The present disclosure provides a method for selective autonomous driving during inference. Method comprises determining, by a computerized system of a vehicle, that the vehicle is approaching a road segment that is deemed to be safe for autonomous driving according to a data structure currently stored in the vehicle. Method further comprises repetitively verifying by the computerized system, in real time, based on sensed information, that the road segment maintains safe. Method also comprises transferring a control over the vehicle to a human driver when facing a verification failure.
A method of training of components within a system for driving, the method includes identifying, by a computerized system, a module in a stack of modules, wherein the identified module is distilled in accordance with a specified driving scenario; freezing at least part of the other modules of the stack; and autonomously training, by the computerized system, the module in an end-to-end training, to contribute to a provision of a driving related decision by the stack of modules, by using a loss function determined based on an output coming out of the stack of modules. The autonomously training of the module, within the stack, occurs while at the least part of the other modules of the stack are in a frozen state.
A method that is computer implemented and is for air and road based real time driving related decisions, the method includes (i) calculating, by a processor of the vehicle and in real time, a relationship between (a) an air based representation of a lane segment as captured by an air based information and (b) a vehicle based representation of the lane segment as captured by a vehicle based information; wherein the air based representation and the vehicle based representation are located in a same virtual plane; and (ii) determining, by the processor and in real time, a slope value indicative of a slope of the lane, based on the relationship and a mapping between relationship values and lane segment elevation profile values.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
A method for continuous real time driving from air, the method includes obtaining, during inference by a computerized system associated with an aerial system, aerial information captured by the aerial system at a period of time and a location corresponding to a driving of one or more different ground vehicles, wherein the aerial system is associated with computerized systems of the one or more different ground vehicles; processing, in real-time by artificial intelligence models of the computerized system, the aerial information with respect to a specified ground vehicle of the one or more different ground vehicles, to provide a driving related decision for the specified ground vehicle for autonomous driving; and communicating, in real-time, the driving related decision to a computerized system associated with the specified ground vehicle.
The present disclosure provides a method of learning from air for autonomous driving. The method includes obtaining an aerial image containing aerial data of a region containing multiple ground vehicles and road objects. The aerial data is analyzed in a machine learning process from respective points of view of the multiple ground vehicles. Based on the analyzing, respective ground vehicle views are produced, each from a respective point of view of a different ground vehicle and including road object information pertaining to the respective point of view of each different ground vehicle, to be applied in training an artificial intelligence (AI) model to be used in driving an autonomous vehicle.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/17 - Terrestrial scenes taken from planes or by drones
G08G 1/01 - Detecting movement of traffic to be counted or controlled
6.
LEARNING OF AUTONOMOUS DRIVING MODELS FROM AIR PER DRIVING SCENARIOS
The present disclosure provides a method of learning from air of scenario-based artificial intelligence models for autonomous driving, the method includes obtaining air based data of a region containing multiple ground vehicles and road objects; analyzing, in a machine learning process, the air based data from respective points of view of the multiple ground vehicles per driving scenario of a range of real-world driving scenarios; and creating, based on the analyzing, corresponding training sets for artificial intelligence models used in autonomous driving of the multiple ground vehicles, wherein the corresponding training sets are created per driving scenario and include road object information pertaining to the respective point of view of the multiple ground vehicles in the driving scenario.
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
7.
ENHANCEMENT OF REAL TIME DRIVING FROM AIR USING LIDAR DATA
A method for air based real time driving related decisions, the method includes obtaining, by a processor of the vehicle, air based information that is indicative of an environment of the vehicle in real-time; and generating, based on the air based information, driving related decisions to be used in autonomous driving. The generating includes (a) determining, by applying an artificial intelligence process on the air based information, light detection and ranging (LIDAR) information generated by a virtual LIDAR of the vehicle; (b) generating a perception of the environment of the vehicle based on the virtual LIDAR information and the air based information; and (c) wherein the driving related decisions to be used in autonomous driving are based on the perception of the environment of the vehicle.
A method for real time predictive driving maneuver assist for autonomous driving applications. The method includes identifying a location of an expected driving maneuver in a driving path of a vehicle, wherein the expected driving maneuver is associated with a scenario in the driving path of the vehicle; collecting statistical data pertaining to artificial intelligence models activated, in a driving of vehicles, in accordance with the scenario; obtaining environmental information regarding an environment of the driving of the vehicle; and determining, in real-time and before the vehicle reaching the location of the expected driving maneuver, by processing the collected statistical data with the environmental information in accordance with the scenario, a set of artificial intelligence models to provide a decision making for assisting with the expected driving maneuver when the vehicle reaches the location of the expected driving maneuver.
The present disclosure provides a method for agentic artificial intelligence agents based driving of an autonomous vehicle. For each location along a driving path: (a) the autonomous vehicle receives from a remote system a local ensemble associated with the environment, the local ensemble comprises narrow artificial intelligence agents and a router that selects agents based on environmental information, (b) feeding the ensemble sensed environmental information, (c) identifying the scenario faced by the vehicle, (d) selecting relevant narrow artificial intelligence agents for that scenario, (e) sending sensed information to selected agents, generating driving decisions by the agents, and (f) executing autonomous driving operations based on those decisions.
A method for establishing drivers'trust through event predictability, the method includes obtaining, at a machine learning process, path information regarding a driving path of a driving by an autonomous vehicle; identifying, by the machine learning process based on the path information, a road scenario that is accommodated, at least in part, in a path segment of the driving path; determining an artificial intelligence model that is below a maturity threshold with respect to providing a decision making to an autonomous driving in the road scenario, through the path segment of the driving path; and generating instructions executable by a human machine interface to trigger, at a planning of the driving path of the driving, a human visible indication in association with the path segment, the human visible indication reflecting a low maturity artificial intelligence model with respect to the autonomous driving in the path segment.
A method of providing artificial intelligence models development access for autonomous based driving. The method includes storing artificial intelligence models each developed across a narrow driving scenario, and data originating from sensory data captured in an environment of a vehicle. Providing a view of the artificial intelligence models or the data. And selectively providing, contingent on a request for use of a distributed storing, to a second group of multiple users a second remote access, the use of the at least one of: the artificial intelligence models or the data. The use is provided by facilitating use of the requested distributed storing to a requesting user, under control of a user in charge of the requested distributed storing.
A method for real time compatibility of artificial intelligence models with regulation scenarios, the method includes selecting, in view of environmental information relating to an initial indication of a driving scenario faced by a vehicle, at least a first artificial intelligence model, to provide an initial driving decision making in accordance with the driving scenario; determining, based on additional incoming data captured in a driving of the vehicle towards the driving scenario, a current indication of the driving scenario faced by the vehicle; and selecting, in real-time and based on the determined current indication, at least a second artificial intelligence model to provide a second driving decision making in accordance with both the initial indication of the driving scenario and the current indication of the driving scenario.
A method of distributed usage of AI based models for driving. The method comprising submitting a request for use of a distributed storage with respect to a requested distributed storing, with an autonomous driving application. The requested distributed storing is at least one of: artificial intelligence models developed across driving scenarios, and data related to driving. And selectively obtaining remote access, based on the submitted request. The remote access involves uploading, downloading, and accessing the requested distributed storing, and facilitated under control of a user in charge of at least one of: the distributed storage, and the requested distributed storing.
A method of predictability of artificial intelligence models for activation using localization, the method includes: (a) obtaining, by a computerized system of a vehicle, cross-statistical data, (b) analyzing, the cross-statistical data with respect to one or more first artificial intelligence models of the first set currently activated in association with the first road segment; and (c) predicting, based on analysis of the cross-statistical data, an artificial intelligence model for activation in a driving of the vehicle when approaching the second road segment. The artificial intelligence models of the first set and of the second set are trained each, in a scenario-level learning, and further, by collecting special-purpose data relating directly to a specified road segment indication and reflecting behavioral data of drivers captured along a specified road segment.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
15.
ENHANCEMENT OF AI MODELS FOR AUTONOMOUS DRIVING PER LOCALIZATION
A method of providing adaptive decision making for autonomous driving applications, the method includes obtaining sensor data input; determining a driving scenario; obtaining a road segment indication; and providing a special-purpose decision making, to an autonomous driving application of the vehicle, that is adaptive to the road segment indication and further in accordance with the driving scenario faced by the vehicle, wherein an artificial intelligence model associated with the special-purpose decision making, is trained, in a scenario-level learning by using sensed data captured in the environment of the vehicle, to provide a scenario-level decision making in accordance with the driving scenario, and further, by collecting special-purpose data relating directly to the road segment indication and reflecting behavioral data of drivers captured along the road segment, to provide a special-purpose decision making that is adaptive to the road segment indication, in accordance with the driving scenario.
A method of generating artificial intelligence (AI) models for driving related scenarios, the method includes (a) generating, by using driving related data, a database of driving scenarios, the generating involves clustering the driving related data in accordance with the driving scenarios; and holding, in the database, the clustered data in association with corresponding driving scenarios; (b) creating, by using the clustered data, a dictionary of concept signatures; and (c) training, by using the database of driving scenarios, a set of AI models, the training of each AI model is based on the clustered data stored in the database in accordance with a specified driving scenario, to provide a decision making with respect to the specified driving scenario.
A method of activation of artificial intelligence models for driving related scenarios, the method includes obtaining sensor data input relating to an environment of a vehicle; generating, in a driving of the vehicle, a signature based on the sensor data input; matching, in the driving of the vehicle, the signature with a set of concept signatures that are held in a dictionary of concept signatures in association with driving scenarios; determining a driving scenario, based on the matching; and generating instructions, executable by a processing unit of the vehicle, to issue a notification for activation of a selected set of artificial intelligence models, in accordance with the driving scenario, wherein the activation of the selected set of artificial intelligence models providing a decision making for the driving scenario with an autonomous driving application associated with the vehicle
A method of self-learning from air of AI models applicable for driving, the method includes obtaining, by a computerized system, aerial image signatures of patches of aerial images that capture at least parts of an environment faced by a vehicle, wherein the computerized system is associated with a set of artificial intelligence models applicable for autonomous driving; identifying, from the aerial image signatures, a set of aerial image signatures in accordance with a specified driving scenario faced by the vehicle; and training, in a self-supervised learning process based, at least in part, on the identifying, a neural network implementing an artificial intelligent model to provide a decision making for the specified driving scenario, wherein the artificial intelligence model is at least one of: a new artificial intelligence model, or one of the set of artificial intelligence models associated with the computerized system.
A method for real time air perception, the method includes continuously obtaining, by a computerized system, aerial image signatures of patches of aerial images in accordance with a determined driving path of the vehicle, such that the patches of aerial images capture at least parts of an environment of the determined driving path for a vehicle; processing, by the computerized system and in real time, the aerial image signatures in accordance with one or more road elements within an environment along the determined driving path of the vehicle; and providing perception results, based on the processing by a classification process running with a neural network in a real time driving of the vehicle, for use in an autonomy-level driving of the vehicle.
A method of interactive neural network training for driving, the method includes identifying, across a first set of images of road elements and using a neural network to output first driving related outcomes, an image comprising a combination of elements in an initial scenario that is below a confidence level threshold; determining the combination in the initial scenario as a bias; interacting, responsive to the determining, with a second set of images, using the neural network to output second driving related outcomes, wherein the second set of images are created, at least in part, artificially; and revoking, with the second process running interactively with the first process, the determined bias in the first process, by interacting with the first process using the second driving related outcomes of the second process.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
21.
AUTOMATIC BIAS RELATED DATASET CREATION FOR MACHINE LEARNING TRAINING
A method of automatic bias related dataset creation for machine learning training, the method includes identifying, via a self-supervised learning process, a sensed information unit that is classification biased as it exhibits a combination of features, the sensed information unit is of a dataset associated with captured data in a road environment; automatically artificially creating a set of sensed information units exhibits only one or only some features of the combination of features; and adding the automatically artificially created set to the dataset to provide an updated data set in association with the identified classification biased sensed information unit for training a machine learning process with the updated dataset to provide a trained machine learning process that identifies each of the combination of features as a separate feature for classification.
A method of a pixel based with object based decision making for driving, the method includes receiving, at a first machine learning process of an artificial intelligence agent, a sensed information unit; receiving, at a second machine learning process of the artificial intelligence agent, object descriptive information regarding an object captured in the sensed information unit; generating, by the first machine learning process, a pixel-based path planning output related to a suggested pixel-based path segment of a vehicle; generating, by the second machine learning process, an object-based path planning output related to a suggested object-based path segment of the vehicle; and generating, by at least in part processing the pixel-based path planning output in correspondence with the object-based path planning output, a driving related output with respect to the vehicle.
A method decorrelated topic based representation of road elements for classification, the method includes obtaining, at a machine learning process, a sparse binary representation corresponding to an initial embedding space of a road element captured in a sensed information unit; and selecting, by checking values of topic information of the sparse binary representation using the machine learning process, a topic, from a set of topics respectively characterized in the initial embedding space, the selected topic corresponding to a reduced space, each of the selected set of topics determined in decorrelation from another topic based on at least in part a measurement of an entropy distribution of bits of the sparse binary representation.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
A method of joint signature-virtual field representation of road elements for driving, the method includes receiving, at a machine learning process associated with a vehicle, multiple sensed information units representing a road element captured at different points of time; generating, by the machine learning process, a joint representation of the road element accounting for a class indication of the road element and of a virtual field indication of an impact of the road element on the vehicle; and determining in real time in a driving of the vehicle, based on the joint representation, a driving related output affecting the vehicle.
A method of using an artificial neural network to generate granular image level representations for driving, the method includes (a) obtaining a sensed information unit that captures a first element, (b) generating, by a machine learning process using the artificial neural network, a first set of tokens for the first element each representing a respective attribute characterizing the first element, (c) processing, by the machine learning process, the first set of tokens in correspondence with at least a second set of tokens generated for a second element, (d) producing, based on the processing, an image-level representation for the first element with respect to the second element, (e) determining, based on the image-level representation, an interaction between the first and second elements in real time; and (f) determining, based on the determined interaction, a driving related output with respect to the vehicle.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
B60W 50/06 - Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
A method of providing a granular image level representation for driving in interaction with unknown elements, the method includes (a) obtaining a sensed information unit that captures an unclassified element in an environment of a vehicle; (b) generating, by a machine learning process (MMP) trained across road elements using an artificial neural network, a first set of tokens for the unclassified element each representing a respective attribute characterizing the unclassified element in the environment; (c) processing, by the MMP, the first set of tokens in correspondence with at least a second set of tokens generated in the environment of the vehicle; (d) determining, based on the processing and according to an image-level representation for the unclassified element, an interaction between the unclassified element and the vehicle in the environment in real time; and (e) determining, based on the determined interaction, a driving related output with respect to the vehicle.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
A method of providing selective learning by prediction for driving, the method includes (a) obtaining, by a machine learning process using an artificial neural network trained across road elements, a first set of tokens with respect to an element captured in a sensed information unit in an environment of a vehicle, the first set of tokens representing respective attributes characterizing the first element; (b) obtaining, by the machine learning process, a second set of tokens generated respect to the vehicle and representing respective attributes characterizing the vehicle; (c) obtaining, by the machine learning process, a scenario indication that is indicative of a scenario faced by the vehicle in the environment; and (d) processing, by the machine learning process, the first set of tokens in correspondence with the second set of tokens and with respect to the scenario.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for fully or partially self-driving vehicles; Downloadable computer software utilizing artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning for operating fully or partially self-driving vehicles; Downloadable software for decision making for fully or partially self-driving vehicles; Downloadable software using artificial intelligence(AI) driven modules for driver assistance and autonomous driving, including perception, scene understanding, localization of vehicle position and surrounding environment, prediction, planning and decision making for fully or partially self-driving or autonomous vehicles, driving policy and planning; Downloadable software that processes vehicle sensor data and camera data to generate bandwidth-efficient transmission that can be shared for cloud-assisted driving intelligence; Downloadable software for use in advanced driver assistance systems (ADAS) and autonomous driving systems to support cloud-assisted reasoning, simulation, and decision support; Downloadable software for collection, processing, analysis, compression, and optimization of vehicle sensor data and driving-related data for use in advanced driver assistance systems (ADAS), autonomous driving systems, and cloud-assisted driving intelligence. Providing offline and online, non-downloadable software for advanced driver assistance systems (ADAS) and for operating fully or partially self-driving vehicles; Providing offline and online non-downloadable computer software utilizing artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning for operating fully or partially self-driving vehicles; Scientific research and advanced product research and development services in the field of driver assistance for fully or partially self-driving vehicles; Scientific research and advanced product research and development services in the field of artificial intelligence and machine learning for fully or partially self-driving vehicles; Software as a service (SAAS) featuring computer software for vehicle localization for fully or partially self-driving vehicles; Software as a service (SAAS) services for providing high-compute driving intelligence for advanced driver assistance systems (ADAS) and autonomous driving systems for cloud-based reasoning, planning, simulation, and decision support; Software as a service (SAAS) featuring computer software for collection, processing, analysis, compression, management, and utilization of driving data, vehicle sensor data, and environmental data for advanced driver assistance systems (ADAS), autonomous driving, simulation, validation, and safety; Cloud-based research and development services for generating, configuring, and updating AI-driven modules for driver assistance and autonomous driving applications; Cloud providing temporary use of online non-downloadable software for building and maintaining digital representations of vehicles and the driving environment to enable prediction, risk assessment, and improved safety; Software engineering services and technology development services for creating AI-driven modules and integrating them into vehicle-based edge computing platforms; Development of new technology and engineering services in the fields of advanced driver assistance systems (ADAS) for autonomous driving software, simulation, validation, and safety.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for fully or partially self-driving vehicles; Downloadable computer software utilizing artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning for operating fully or partially self-driving vehicles; Downloadable software for decision making for fully or partially self-driving vehicles; Downloadable software using artificial intelligence(AI) driven modules for driver assistance and autonomous driving, including perception, scene understanding, localization of vehicle position and surrounding environment, prediction, planning and decision making for fully or partially self-driving or autonomous vehicles, driving policy and planning; Downloadable software that processes vehicle sensor data and camera data to generate bandwidth-efficient transmission that can be shared for cloud-assisted driving intelligence; Downloadable software for use in advanced driver assistance systems (ADAS) and autonomous driving systems to support cloud-assisted reasoning, simulation, and decision support; Downloadable software for collection, processing, analysis, compression, and optimization of vehicle sensor data and driving-related data for use in advanced driver assistance systems (ADAS), autonomous driving systems, and cloud-assisted driving intelligence Providing offline and online, non-downloadable software for advanced driver assistance systems (ADAS) and for operating fully or partially self-driving vehicles; Providing offline and online non-downloadable computer software utilizing artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning for operating fully or partially self-driving vehicles; Scientific research and advanced product research and development services in the field of driver assistance for fully or partially self-driving vehicles; Scientific research and advanced product research and development services in the field of artificial intelligence and machine learning for fully or partially self-driving vehicles; Software as a service (SAAS) featuring computer software for vehicle localization for fully or partially self-driving vehicles; Software as a service (SAAS) services for providing high-compute driving intelligence for advanced driver assistance systems (ADAS) and autonomous driving systems for cloud-based reasoning, planning, simulation, and decision support; Software as a service (SAAS) featuring computer software for collection, processing, analysis, compression, management, and utilization of driving data, vehicle sensor data, and environmental data for advanced driver assistance systems (ADAS), autonomous driving, simulation, validation, and safety; Cloud-based research and development services for generating, configuring, and updating AI-driven modules for driver assistance and autonomous driving applications; Cloud providing temporary use of online non-downloadable software for building and maintaining digital representations of vehicles and the driving environment to enable prediction, risk assessment, and improved safety; Software engineering services and technology development services for creating AI-driven modules and integrating them into edge-vehicle; Development of new technology and engineering services in the fields of advanced driver assistance systems (ADAS) for autonomous driving software, simulation, validation, and safety
A method for non-verbal traffic-directed human communication, that includes obtaining a sensed information unit that captures a non-verbal communication attempt made by a person in relation to a vehicle; determining whether the non-verbal communication attempt conveys a legally binding driving related command, by processing, using a machine learning process, the sensed information; automatically generating instructions executable by a man machine interface controller, in accordance with the determination; and providing, based on the generated instructions, at least one of a human perceivable, and machine-perceivable indication regarding the legally binding driving related command.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software using artificial intelligence (AI) driven modules for driver assistance and autonomous driving, including perception, scene understanding, localization of vehicle position and surrounding environment for fully or partially self-driving or autonomous vehicles, driving policy and planning; Downloadable software that processes vehicle sensor data and camera data to generate bandwidth-efficient transmission that can be shared for cloud-assisted driving intelligence; Downloadable software for use in advanced driver assistance systems (ADAS) and autonomous driving systems to support cloud-assisted reasoning, simulation, and decision support. Software as a service (SAAS) services for providing high-compute driving intelligence for advanced driver assistance systems (ADAS) and autonomous driving systems for cloud-based reasoning, simulation, and decision support; Cloud-based research and development services for generating, configuring, and updating AI-driven modules for driver assistance and autonomous driving applications; providing temporary use of online non-downloadable software for building and maintaining digital representations of vehicles and the driving environment to enable prediction, risk assessment, and improved safety through cloud computing; Software engineering services and technology development services for creating AI-driven modules and integrating them into edge-vehicle; Development of new technology and engineering services in the fields of advanced driver assistance systems (ADAS) for autonomous driving software, simulation, validation, and safety.
A method for incremental learning classification capabilities, the method includes identifying, at each iteration of an iterative incremental learning process, that an embedding exhibits a clustering confidence level that is below a threshold, the embedding, generated at least in part by a machine learning process, representing a detector output that is responsive to a sensed information unit; identifying, at each iteration by accessing a data structure associated with one or more reference detector output, signatures that are similar to a signature of the detector output; and determining, at each iteration, an additional cluster for an embedding associated with the detector output and for reference embeddings associated with the one or more reference detector output signatures. Such that at each iteration of the iterative incremental process the identifying is based on at least one more determined cluster than a preceding iteration, and road elements associated with embeddings that fall within the determined cluster exhibit a clustering confidence level that is above the threshold and are classified, during inference, in accordance with the determined cluster.
A method for self-supervised learning of ambiguous zone embedding space, the method includes identifying, by a processing circuit and during a validation process of a first neural network, a set of embeddings that represent a group sensed information units that are associated with a classification confidence level below a threshold; wherein the first neural network was trained by a supervised training process; the set of embeddings defining an ambiguous zone; and triggering a training of a second neural network, in a self-supervised learning process, across the group of sensed information unit.
A method of AI models generalization for driving. The method includes identifying road segments artificial intelligence models based on a similarity metric between different road segments along one or more different driving routes and further in accordance with a route benchmark. Each road segments artificial intelligence model is generated in association with a road segment for the driving route, by collecting driving data relating directly to the road segment and reflecting behavioral data of drivers captured along the road segment. And creating a general artificial intelligence model for at least a portion of the driving route, by automatically merging at least a portion of the road segments artificial intelligence models for the different road segments based on the similarity metric, to provide a decision making that complies with the different road segments along the one or more different driving routes.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
A method of AI models generalization across different road segments. The method includes identifying, by a computerized system, a similarity metric between a first road segment and a second road segment. The first road segment is associated with a first artificial intelligence model generated in association with the first road segment by collecting driving data relating directly to the first road segment and reflecting behavioral data of drivers captured along the first road segment to provide a decision making that is adaptive to the first road segment. And generating a second artificial intelligence model in association with the second road segment based on either the first artificial intelligence model, or a first dataset fed to the first artificial intelligence model during a generating of the first artificial intelligence model, to provide a decision making that is adaptive to the second road segment.
A method of automatically identifying faulty representations across far-near classification detections, the method includes continuously obtaining, across a specified period of time, classification decisions for a road element, where the road element is trackable by using at least one sensing unit across the specified period of time and across a range of distances from the at least one sensing unit, automatically searching, by a machine learning process, for a discrepancy between classification decisions made at different distances of the range of distances; determining in real time, based on an outcome of the automatically searching whether the detections made with respect to the road element are faulty; and providing a faulty representation indication with respect to the classification decisions for the road element.
A method of producing a group of neural networks, the method includes determining a first layer potion that is shared by a first neural network sub-group of the group; determining second layer portions that are sharable by second neural network sub-groups, such that different second layer portions are shared by different second neural network sub-groups of the group; and determining third layer portions that are sharable by third neural network sub-groups, such that different third layer portions are shared by different third neural network sub-groups of the group; wherein each neural network of the group further comprises a unique combination of layer portions.
A neural network training method for autonomous driving, the method includes (i) obtaining, by a computer device, features generated by a neural network and representing a first augmented image and at least a second augmented image, where the first augmented image and at least the second augmented image are different augmented image versions of a training image; (ii) determining, by the computer device, one or more an angular related losses based on the first augmented image and the second augmented image; (iii) determining a contrastive learning loss based on the first augmented image and the second augmented image; and (iv) updating the neural network based on the one or more angular related loss and on the contrastive learning loss.
G06T 11/60 - Editing figures and textCombining figures or text
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
39.
CUSTOMIZED PROTOTYPE BASED TRAINING FOR EMBEDDING CLASSIFICATIONS
A method for training a neural network, the method includes obtaining first augmentation image features and second augmentation image features for a training image associated with a specified class; selecting, out of different sets of contrastive learning loss prototypes, a set of contrastive learning loss prototypes associated with the specified class; wherein the different sets of contrastive learning loss prototypes are associated with different classes; determining a contrastive learning loss on the first augmentation image features and the second augmentation image features, using the selected set of prototypes; and updating the neural network based on the determined contrastive learning loss.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/44 - Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersectionsConnectivity analysis, e.g. of connected components
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
A method that includes (i) generating, in a first iterative process, a first signature comprising first identifiers that are indicative of at least one of (a) a feature of a road element associated with the first signature or (b) a feature of a generation of the first signature, the first identifiers being generated in correlation to each other, and (ii) generate, in a second iterative process, a second signature comprising second identifiers that are indicative of (a) a feature of a road element associated with the second signature or (b) a feature of a generation of the second signature, the second identifiers being generated in correlation to each other; wherein the second identifiers of the second signature are generated in de-correlation to the first identifiers of the first signature, and wherein the first signature and the second signature collectively represent a cluster of sensed information.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software using artificial intelligence (AI) driven modules for driver assistance and autonomous driving, including perception, scene understanding, localization of vehicle position and surrounding environment for fully or partially self-driving or autonomous vehicles, driving policy and planning; Downloadable software that processes vehicle sensor data and camera data to generate bandwidth-efficient transmission that can be shared for cloud-assisted driving intelligence; Downloadable software for use in advanced driver assistance systems (ADAS) and autonomous driving systems to support cloud-assisted reasoning, simulation, and decision support Software as a service (SAAS) services featuring software for providing high-compute driving intelligence for advanced driver assistance systems (ADAS) and autonomous driving systems for cloud-based reasoning, simulation, and decision support; Cloud-based research and development services for generating, configuring, and updating AI-driven software modules for driver assistance and autonomous driving applications; Providing temporary use of online non-downloadable cloud computing software for building and maintaining digital representations of vehicles and the driving environment to enable prediction, risk assessment, and improved safety; Software engineering services and technology development services for creating AI-driven software modules and integrating them into edge-vehicle; Development of new technology and engineering services in the fields of advanced driver assistance systems (ADAS) for autonomous driving software, simulation, validation, and safety
A method for real time analysis, the method includes producing, by a classification unit having a neural network, classification decisions for sensed information units obtained in an environment of a vehicle; automatically generating, by one or more computing devices and having auto-labeling capabilities running in a real-time driving of the vehicle, an automated ground truth labeling for a determined set of sensed information units; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to the classification detection; and responsive to the detecting, addressing the detected issue in the real-time driving of the vehicle, using a signature associated with at least the classification decision or the detected issue. The neural network is in a same state in the producing the classification decision, detecting the issue, and addressing the issue.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/70 - Labelling scene content, e.g. deriving syntactic or semantic representations
According to an embodiment, there is provided a method for contextual attribute-based perception, the method includes obtaining, by a processing circuit, contextual attributes generated at a machine learning process in association with a detected road element; identifying a selected group of contextual attributes in accordance with one or more criteria; and making, by the processing circuit, a determination with respect the detected road element, based on the selected group of contextual attributes
A method that is computer implemented and is for data layer augmentation, the method includes obtaining, by a processor associated with a vehicle, a data layer associated with road elements of a specified type; obtaining, by a processor associated with a vehicle, localization information regarding a location of the vehicle, wherein the road element information is obtained based on aerial image information within a region of a vehicle and on environmental information sensed by the vehicle; and augmenting the data layer using the localization information, wherein the augmenting of the data layer comprises populating a database with data representing updated road elements location for a group of road elements of the specified type within the region of the vehicle.
A method for upgrading classification capabilities, the method includes (a) obtaining, by a processing circuit, an obtained representative vector representing a new class being unfamiliar to a classification neural network and was learnt during a one-shot learning process; (b) producing a new class representative vector in correspondence with the new class based on a classification parameter related to the obtained representative vector, and in correspondence with an existing class representative vector that represents an existing class, wherein the classification neural network is trained to identify the existing class; and (c) configuring a classification unit that is associated with the classification neural network to identify the new class using the new class representative vector, and absent weights amendments of the classification neural network.
A method for classification process evaluation, the method includes (a) receiving, at a processing circuit, classification data generated by a classification process for augmented versions of a test sensed information unit; (b) evaluating the classification data across the augmented versions, by analyzing a distribution of, at least, selected classification values of the classification data; (c) determining, based on the evaluation, a compatibility of the classification process with respect to the received classification data; and (d) issuing a compatibility indication in accordance with the determined compatibility, the compatibility indication indicative of the compatibility of the classification process to classify an element captured by the sensed information unit.
A method for dynamic classification for autonomous driving, the method includes (i) producing, by a classification neural network associated with a driving of a vehicle, a catalog sample representative vector representing a catalog sample of a new class for autonomous driving being unidentified by the classification neural network at the time of the driving; (ii) generating, by the classification neural network, a new image-based representative vector representing an image of an entity of the new class; and (iii) classifying, by a classification unit that is associated with the classification neural network, the entity as being associated with the new class.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
A method that is computer implemented and is for perception related processes, the method includes (i) receiving, by a processing circuit of the vehicle, scenario information about a scenario faced by a vehicle; wherein the scenario information includes environmental information about an environment of the vehicle; (ii) identifying the scenario, by the processing circuit, using the received scenario information; (iii) determining, based on the identified scenario, a resource operation parameter that conform to the identified scenario and is related to operation of a perception related process; and (iv) making the resource operation parameter available in the operation of the perception related process.
B60W 40/12 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to parameters of the vehicle itself
49.
Way point generation for smoother actuation using machine learning model
There is provided a method for training of machine learning processes for autonomous driving applications, the method includes (a) receiving a training dataset that includes images acquired during a driving episode of a vehicle, the images associated with inertial measurement unit information that includes velocity values and yaw rate values; (b) estimating, based on the images and the inertial measurement unit information, waypoints indicative of waypoints passed by the vehicle during the driving episode; and (c) training a machine learning process using the images and the estimated waypoints, to produce a predictable set of future waypoints indicative of future waypoints on a driving route of a vehicle.
G06T 7/70 - Determining position or orientation of objects or cameras
G06V 10/00 - Arrangements for image or video recognition or understanding
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
50.
Training of machine learning processes for autonomous driving applications
A method for training of machine learning processes, the method includes (a) obtaining, at a first computerized process, an identified signature, the identified signature identified at a second computerized process based on an overlap between a first top matching of signatures that are untagged and randomly obtained and a second top matching of signatures that are untagged and are correctly or erroneously indicative of a detection of a reference classification; and (b) training, by the first computerized process, a machine learning process using a training dataset of signatures and further based on the identified signature, to provide determinations for the reference classification with respect to an automated driving application.
A computer-implemented method for sensor fusion in relation to at least partially autonomous driving of a vehicle. The method may include obtaining first signatures of first patches of a first type sensed information unit (SIU) that was sensed by a first sensor of a first type; obtaining second signatures of second patches of a second type SIU that was sensed by a second sensor of a second type, the second type differs from the first type; wherein the first sensor and the second sensor are associated with the vehicle; finding correlations by applying a correlation function between the first signatures and the second signatures; wherein the finding is executed by a mapping system; and determining, based on the correlations and by the mapping system, a mapping between the first patches and the second patches, the mapping to be used in an at least partially autonomous driving of a vehicle; wherein the correlation function having been developed by applying a supervised machine learning process based on relationships between members of training signature pairs, each training signature pair comprises a first sensor training signature and a second sensor training signature of a same object.
A method that includes obtaining, by a processor associated with the vehicle, a cross-view based localization of the vehicle that is determined by using air based data in accordance with environmental information sensed by a sensor of the vehicle at the region of the vehicle. Then, obtaining, by accessing a database that is populated to contain a data layer, data layer information regarding locations of a given road setting within the region of the vehicle; obtaining, in real time, ground detection output that is being generated for the given road setting by a perception unit of the vehicle; and providing real-time fine-tuned localization of the vehicle, by continuous alignment of the ground detection output in accordance with the data layer information, for the given road setting.
A method for monitoring road markings in an environment of a vehicle, the method includes (a) receiving by a processing circuit, information about the environment; (b) identifying, based on the information about the environment, a road marking that is located within the environment; and (c) applying an object-based approach, on the road marking using the identified information.
A method that is computer implemented for self-learning of relevancy metrics for perception related applications, the method comprising: receiving a training dataset that comprises (i) scenario information regarding a scenario faced by a vehicle and involving a road user, and (ii) behavior information indicative of a response of the vehicle to a presence of the road user; determining, based on the scenario information and the behavior information, a relevancy metric providing an indication of an impact of the road user on a driving of the vehicle; and training, using self-learning, a machine learning process to infer the relevancy metric according to the scenario.
A method that is computer implemented and is for adaptable image signal processing for a vehicle, the method includes (i) receiving, by a processing circuit, environmental information about an environment of the vehicle; the environmental information being generated based in part on processing of images using a first image signal processing configuration; (ii) analyzing, by the processing circuit, the received environmental information to determine a scenario as represented by the environmental information; (iii) determining, by the processing circuit and based on the analyzing, a second image signal processing configuration that corresponds to the scenario; and (iv) providing a prompt indicative of a need to change the processing of incoming images captured along the determined scenario using the second image signal processing configuration.
A method for providing an explainable artificial intelligence-based representation for at least partially autonomous driving applications includes receiving environment information relating to an environment in which a vehicle is present and detecting a plurality of discrete elements in the environment. The method includes generating resource allocation information relating to the plurality of discrete elements and, based on the generating step, selecting an artificial intelligence resource for processing a selected discrete element. The artificial intelligence resource is trained to identify a collection of detectable objects or characteristics in the driving environment, the collection of detectable objects or characteristics includes the selected discrete element, and the artificial intelligence resource is associated with a semantic element. The method includes identifying the discrete element as one of the detectable objects or characteristics, and producing the explainable artificial intelligence-based representation of the selected discrete element or an action relating to the selected discrete element.
G06V 20/40 - ScenesScene-specific elements in video content
B60W 50/14 - Means for informing the driver, warning the driver or prompting a driver intervention
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
57.
DOWNSTREAM PROCESSING OF EMBEDDING INFORMATION ITEMS
A method for downstream processing of embedding information items, the method includes (i) receiving multiple evaluated element embedding information items that represent multiple evaluated elements within an environment of a vehicle; (ii) identifying that the multiple evaluated element embedding information items are classified into an insufficient confidence level; and (iii) for each one of the multiple evaluated embedding information items identified as an being classified into the insufficient confidence level, automatically routing evaluated element information to a corresponding embedding information item-based classification unit that is trained to classify elements represented by the evaluated element embedding information item associated with the corresponding population of embedding information items.
G06F 18/2135 - Feature extraction, e.g. by transforming the feature spaceSummarisationMappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
A method for object classification comprising receiving, by a processing circuit, a sensed information unit that includes information indicative of an object located within a vehicle environment, dynamically generating, by the processing circuit, an embedding of the object. The embedding is a discriminating feature vector representing the object. The method comprises comparing the embedding to a plurality of reference embedding clusters. Each of the plurality of reference embedding clusters is associated with an object classification of a plurality of reference objects. The method comprises classifying, based on the comparing step, the embedding as being associated with one of the plurality of reference embedding clusters.
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/40 - Extraction of image or video features
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
A method for travel lane element classification, including obtaining, via a processing circuit, information indicative of a travel lane including one or more travel lane elements located within an environment of a vehicle; generating a plurality of keypoints from the information; organizing the plurality of keypoints into one or more subgroups of keypoints, wherein each of the one or more subgroup of keypoints is indicative of one or more categories of travel lane elements; generating one or more embeddings of the one or more subgroup of keypoints, and classifying, based on the one or more embeddings, the one or more organized subgroup of keypoints as indicative of a travel lane marker. The classifying triggers a determination of a driving related operation to be executed by the vehicle.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 10/762 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for fully, or partially self-driving or autonomous vehicles; Downloadable software for localization for fully or partially self-driving or autonomous vehicles; Downloadable software for vehicle navigation for fully or partially self-driving or autonomous vehicles; Downloadable software for mapping for fully or partially self-driving and vehicles, autonomous vehicles, and/or moving vehicles; Downloadable computer software for artificial intelligence models, machine learning, neural networks, deep learning, and supervised and unsupervised learning; Downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving using aerial and satellite data. Non-downloadable software for advanced driving assistance systems; Nondownloadable software for fully or partially self-driving or autonomous vehicles; Non-downloadable software for localization for fully or partially self-driving or autonomous vehicles; Non-downloadable software for vehicle navigation; Software as a service (SAAS) featuring computer software for fully or partially selfdriving or autonomous vehicles; Software as a service (SAAS) featuring computer software for localization, vehicle navigation, and mapping; Non-downloadable software for mapping for fully or partially self-driving vehicles; Non-downloadable computer software for artificial intelligence models, machine learning, and deep learning; Non-downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving technology.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for generating and matching aerial imagery-derived reference data with data derived from onboard vehicle sensors for use in advanced driving assistance systems; Downloadable software for generating and matching aerial imagery-derived reference data with data derived from onboard vehicle sensors for use in fully, or partially self-driving or autonomous vehicles; Downloadable software for localization of vehicle position and surrounding environment for fully or partially self-driving or autonomous vehicles; Downloadable software for vehicle navigation for fully or partially self-driving or autonomous vehicles; Downloadable software for mapping for fully or partially self-driving and vehicles, autonomous vehicles, and/or moving vehicles; Downloadable computer software for artificial intelligence models, machine learning, neural networks, deep learning, and supervised and unsupervised learning; Downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving using aerial and satellite data Providing online use of non-downloadable software for generating and matching aerial imagery-derived reference data with data derived from onboard vehicle sensors for use in advanced driving assistance systems; Providing online use of non-downloadable software for matching aerial imagery with real-time ground view from the vehicle's cameras for use in fully or partially self-driving or autonomous vehicles; Providing online use of non on-downloadable software for localization of localization of vehicle position and surrounding environment for fully or partially self-driving or autonomous vehicles; Providing online use of non-downloadable software for vehicle navigation; Software as a service (SAAS) featuring computer software for generating and matching aerial imagery-derived reference data with data derived from onboard vehicle sensors for use in fully or partially self-driving or autonomous vehicles; Software as a service (SAAS) featuring computer software for localization of vehicle position and surrounding environment, vehicle navigation, and mapping; Providing online use of non-downloadable software for mapping for fully or partially self-driving vehicles; Providing online use of non-downloadable computer software for artificial intelligence models, machine learning, and deep learning; Providing online use of non-downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving technology.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for remote sensing data collection, training and validation of narrow AI modules for autonomous driving based on localized driving patters, for use in advanced driving assistance systems; Downloadable software namely, remote sensing simulation of data for training and validation of narrow AI modules for autonomous driving, real-time redundancy and supervisory control software for safety and decision-making, and software for generating, enhancing and updating high-resolution environmental data for use in fully, or partially self-driving or autonomous vehicles; Downloadable software for localization of vehicles, static objects, and road users; Downloadable software for vehicle navigation for fully or partially self-driving or autonomous vehicles; Downloadable software for mapping for fully or partially self-driving and vehicles, autonomous vehicles, and/or moving vehicles; Downloadable computer software for artificial intelligence models, machine learning, neural networks, deep learning, and supervised and unsupervised learning; Downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving using aerial remote and satellite data; All of the foregoing excludes software or devices intended for direct human use, including safety alerts, point-of-interest notifications, vehicle dashboards or diagnostics, interactive social platforms, and navigation aids based on static mapping databases Providing online or offline use of Non-downloadable software for remote sensing data collection, training and validation of narrow AI modules for autonomous driving based on localized driving patters for use in advanced driving assistance systems; Providing online or offline use of Non-downloadable software for remote sensing simulation of data for training and validation of narrow AI modules for autonomous driving, real-time redundancy and supervisory control software for safety and decision-making, and software for generating, enhancing and updating high-resolution environmental data for use in fully or partially self-driving or autonomous vehicles; Providing online or offline use of Non-downloadable software for localization of vehicles, static objects, and road users for fully or partially self-driving or autonomous vehicles; Providing online or offline use of Non-downloadable software for vehicle navigation; Software as a service (SAAS) featuring computer software for real-time remote sensing redundancy software providing enhanced environmental perception, predictive decision-making, safety supervision and emergency control, and software for enhancing and updating high-resolution data, including imagery, maps and data layers for use in fully or partially self-driving or autonomous vehicles; Software as a service (SAAS) featuring computer software for localization using signature matching between ground-view data, vehicle sensors, and remote sensing data collection, namely, Non-downloadable software for mapping for fully or partially self-driving vehicles; Providing online or offline use of Non-downloadable computer software for artificial intelligence models, machine learning, and deep learning; Providing online or offline use of Non-downloadable software for data collection, training and validation in the fields of artificial intelligence (AI), machine learning, and deep learning for autonomous driving technology; All of the foregoing excludes non-downloadable software intended for direct human use, including safety alerts, point-of-interest notifications, vehicle dashboards or diagnostics, interactive social platforms, and navigation aids based on static mapping databases
63.
SELECTIVE DOWNLOADING OF AERIAL IMAGE SIGNATURES FOR LOCALIZATION OF DRIVING
A method for using aerial image information, the method includes dynamically determining, by a controller associated with a vehicle, one or more downloading parameters of a downloading of a batch of aerial image signatures; and controlling, by the controller, the downloading of the batch of the aerial image signatures to a memory unit associated with the vehicle for use with vehicle sensed information signatures in a localization of the vehicle.
A method for determining a location of a vehicle includes obtaining, by a processor, a plurality of aerial image segment signatures of segments of a region including the vehicle, and a plurality of sensed image signatures associated with the region including the vehicle. The method matches a selected aerial image segment signature segment signatures to a selected sensed image signature. Based on the matching step, the processor generates probabilistic location information regarding the location of the vehicle. The method also includes generating a movement estimate of the vehicles. The movement estimate is generated based on a vehicle location comparison across a plurality of vehicle sensed images, and the plurality of vehicle sensed images are captured at a plurality of time intervals. The method also includes determining the location of the vehicle by combining the movement estimate of the vehicle and the probabilistic location information.
A method of training a neural network model based on a latent representation including a human-interpretable data representation necessary for performing a specified task. The method includes obtaining an input data, training the neural network model based on the obtained input data; fixing a gauge function by applying an auxiliary loss function on a latent activation for the specified task, during the training of the neural network model to minimize redundancy, and producing a human-interpretable representation of the latent representation of the neural network model, based on the application of the auxiliary loss function on the latent application.
A method for improving an accuracy of object classification, the method includes: (i) receiving, by a machine learning process, information regarding an environment of a vehicle; (ii) classifying, by the machine learning process, an object that is located within the environment of the vehicle to a certain class; wherein the machine learning process was trained by a training process to classify objects while avoiding false positive (FP) errors that are represented by different FP data sets that are fed to the machine learning process during the training process, the different FP data sets are associated with different classes; wherein for each class of the different classes, a FP data set that is associated with the class comprises FP data sub-sets that are associated with different objects that were mistakenly classified to the class; and outputting an outcome of the classification for use in navigating the vehicle.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
67.
VISUALIZING NEURONS IN AN ARTIFICIAL INTELLIGENCE MODEL
A method for visualizing neurons in an Artificial Intelligence (AI) model for autonomous driving. The method includes obtaining, from a number of neurons of the AI model for a task, one or more neurons; determining, for each of the one or more neurons, a respective Region of Interest (ROI) of an input related to the task, wherein the respective ROI is encoded by the one or more neurons for the task; and producing a human-interpretable representation of the determined respective ROI of the input for at least a portion of the one or more neurons, by applying a first operation including Layer-wise Relevance Propagation (LRP).
A method for tracking an object in one or more image frames is disclosed. The method includes: obtaining a first image frame including the object; determining a first set of key points of the object in the first image frame and a first set of descriptors associated with the first set of key points; determining a second set of key points from the first set of key points and a second set of descriptors from the first set of the descriptors; and generating a bounding box of the object based on the second set of key points and descriptors.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
A method for calibration of a camera of a vehicle is disclosed. The method includes: obtaining a first image frame by the camera including an object; obtaining a second image frame by the camera including the object; determining a first set of key points of the object in the first image frame; determining a second set of key points of the object in the second image frame; obtaining a first spatial information about the first set of key points from a non-volatile memory; obtaining a second spatial information about the second set of key points from the same or a different non-volatile memory; and auto-calibrating the camera based on the first and the second spatial information.
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
A method for distance estimation of an object from a vehicle is disclosed. The method includes: obtaining an image frame including the object; identifying a first set of key points of the object from the image frame; obtaining a second set of key points that correlates to the first set of key points from a non-volatile memory; obtaining spatial information about the second set of key points from the non-volatile memory; and evaluating a distance of the object from the vehicle based on the first set of key points and the spatial information about the second set of key points.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06V 10/46 - Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]Salient regional features
A method for transfer learning, including (a) obtaining new object images and new object bounding shape information indicative of new object bounding shapes; (b) feeding the new object images to a NN that is trained to detect the certain objects, (c) providing, per each layer out of a group of candidate layers and for each new object image of the new object images, (i) a features map regarding a new object bounding shape, and (ii) a features map regarding an external region; (d) building, per each layer out of a group of candidate layers of the NN, an object classifier configured to distinguish between a bounding shape region and an external region; (e) selecting, out of the group of candidates layers, a selected layer; and (f) associating the selected layer with a detection of the new object.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/77 - Processing image or video features in feature spacesArrangements for image or video recognition or understanding using pattern recognition or machine learning using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]Blind source separation
A method that is computer implemented and is for improving an accuracy of object detection, the method includes identifying, by a controller, an erroneous signature of at least a part of a sensed information unit (SIU) for use in the object detection, wherein a source of an error of the erroneous signature is a sensing unit that generated the SIU under a current acquisition condition, wherein the at least part of the SIU captured an object; and triggering an acquisition of a new SIU, under a desired acquisition condition that is tailored to solve the error.
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
A method that is computer implemented and is for solving an error related to an object captured in a sensed information unit (SIU), the method includes obtaining a cluster signature that is identified as introducing an error in relation to an object associated with a cluster, the cluster is represented by the cluster signature, the cluster signature is for used for at least partially automatically driving a vehicle; obtaining a compressed version of the cluster signature; and determining whether the compressed version of the cluster signature resolves the error. When determined that the compressed version of the cluster signature resolves the error, automatically replacing the signature by the compressed version of the cluster signature. When determined that the compressed version of the cluster signature does not resolve the accuracy, then triggering a generation of an error resolving process that differs from the compressing of the cluster signature.
A method that is computer implemented and is for solving inaccuracies associated with object detection, the method includes automatically evaluating, by a controller, an accuracy of signatures for use in the object detection, the signatures were generated by an adaptable artificial intelligence (AI) system; and when finding an erroneous signature of the signatures, by the controller, triggering a generation of a router that routes a sensed information unit (SIU) that is associated with the erroneous signature to a current error resolving part of the adaptable AI system, the current error resolving part of the adaptable AI system is currently associated with resolving at least one other error associated with at least one other erroneous signature.
A method that is computer implemented and is for signature generation, the method includes receiving readout information, by a signature generator, the readout information is provided by a readout circuit and was extracted from a deep neural network (DNN) that was fed by a processed sensed information unit (SIU); wherein the processed SIU consists essentially of (i) SIU elements that are located within a region that is related to a bounding shape and has a desired receptive field, and (ii) padding SIU elements; and generating, by the signature generator and based on the readout information, a signature of the processed SIU for use in an at least partially autonomous driving of a vehicle.
A method for solving inaccuracies associated with object detection, the method includes automatically evaluating, by a controller, an accuracy of signatures for use in the object detection, the signatures were generated by an adaptable artificial intelligence (AI) system. When finding an erroneous signature of the signatures, by the controller, triggering a generation of an error resolving part of the adaptable AI system for generating a correct signature instead of the erroneous signature, wherein the erroneous signature, when used for the object detection, results in an object detection error.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
G01S 13/93 - Radar or analogous systems, specially adapted for specific applications for anti-collision purposes
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/98 - Detection or correction of errors, e.g. by rescanning the pattern or by human interventionEvaluation of the quality of the acquired patterns
G08G 1/0967 - Systems involving transmission of highway information, e.g. weather, speed limits
H04W 4/40 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
A method that is computer implemented and is for improving an accuracy of a deep neural network (DNN) used for classification, the method includes identifying an error source within the DNN, wherein the DNN represents a deep learning model used for at least partially autonomous driving; and triggering a generation of a bypass path that bypasses the errors source.
A method that is computer implemented for improving an accuracy of a neural network (NN) used for classification, the method includes obtaining a signature generated by a signature generator, the signature represents at least a part of a sensed information unit (SIU); calculating, by a controller, a distance between the signature and a reference signature that is associated with an error; and determining, by the controller, that the signature is associated with the error when the distance does not exceed a distance threshold. The reference signature is a cluster signature that represents a cluster of signatures, the cluster of signatures includes (i) first signatures that are determined, during a supervised learning process associated with at least partially autonomous driving, to be associated with the error; and (ii) second signatures that are generated during an unsupervised learning process for the autonomous driving scenario, and exhibit a defined similarity with the first signatures.
A method that is automatically validating of signatures for object detection, the method includes automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature introduced an error in a previously accurate detection of an object; and triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
80.
Solving inaccuracies associated with object detection
A method that is computer implemented and is for solving inaccuracies associated with object detection, the method includes automatically evaluating, by a controller, an accuracy of signatures for use in the object detection, the signatures were generated by an adaptable artificial intelligence (AI) system. When finding an erroneous signature of the signatures, by the controller, triggering a generation of (a) a narrow AI agent configured to solve an error associated with the erroneous signature and (b) a router that routes a sensed information unit (SIU) associated with the erroneous signature to the narrow AI agent, wherein the erroneous signature, when used for the object detection, results in an object detection error.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
G01S 13/93 - Radar or analogous systems, specially adapted for specific applications for anti-collision purposes
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/98 - Detection or correction of errors, e.g. by rescanning the pattern or by human interventionEvaluation of the quality of the acquired patterns
G08G 1/0967 - Systems involving transmission of highway information, e.g. weather, speed limits
H04W 4/40 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
81.
METHOD FOR REDUCING COMPUTATIONAL COST FOR AUTONOMOUS DRIVING SYSTEM
A method for reducing the computational cost for an autonomous driving system is disclosed. The method may include the following steps: a) acquiring data related to a task for operating a vehicle; b) training a deep learning model using the data acquired, wherein the deep learning model includes an encoder and a policy head for the task; c) reducing a complexity of the data acquired in step a) by passing the data to the encoder to produce a compressed latent representation of the data; and d) determining a driving operation by the policy head using the compressed latent representation of the data.
A method for real time management of detected issues, the method includes producing, by a classification unit having a neural network, a classification decision for sensed information obtained in an environment of a vehicle; generating, by one or more computing devices with auto-labeling capabilities, an automated ground truth labeling for the sensed information; detecting, by the one or more computing devices and based on a performance indication related to the automated ground truth labeling, an issue with respect to the classification decision; and responsive to the detecting, addressing the detected issue in a driving in the environment of the vehicle by a computer device associated with the vehicle, using a signature generated in association with at least the classification decision or with the detected issue. The neural network is in a same state in the producing of the classification decision, the detecting the issue, and the addressing the detected issue.
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
83.
ACCURATE BOX LOCALIZATION FOR AUTOMATIC TAGGING SYSTEM USING PHYSICAL GROUND TRUTH
A method for segmentation-based generation of bounding shapes, the method may include obtaining bounding shapes that are indicative of objects, the objects were captured in a sensed information unit; generating a cropped image for each bounding shape; segmenting each cropped image to a cropped image background and a cropped image foreground; and generating, for each cropped image, an updated bounding shape that are indicative of dimensions of the cropped image foreground of the cropped image, to provide updated bounding shapes.
A method for calculating a dimension of an object, the method comprises: (a) receiving an image that was acquired by a vehicle camera of a vehicle; the image captures the horizon, the object, and road lane boundaries; (b) determining an initial row-location horizon estimate and a row-location contact point estimate, the row-location contact point estimate represents a contact between the object and a road on which the vehicle is positioned; (c) determining a vehicle camera pitch angle correction and an actual vehicle camera pitch angle, wherein the vehicle camera pitch angle correction, once applied, will cause the road lanes boundaries to be parallel to each other in a real world; (d) calculating the distance between the vehicle and the object based the determined values; and (e) determining the dimension of the object based on the focal length of the vehicle camera, a corresponding dimension of the object within the image and the distance between the vehicle camera and the object.
A method for lane detection, the method includes (a) determining, by a lane detection neural network (NN) and based on locations of one or more road lanes within an aerial image, locations of the one or more road lanes on a ground vehicle acquired (GVA) image; and (b) responding to the determining of the locations of the one or more road lanes on the GVA image. The lane detection NN was trained to perform aerial-images-to-GVA-images conversion. The aerial image was generated by a first NN, based in the GVA image. The first NN was trained to perform GVA-images-to-aerial-images conversion. The GVA image was acquired by a two dimensional camera of a ground vehicle. The one or more locations of the one or more road lanes within the aerial image are provided by a second NN that was trained to perform lane detection in arial images.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for fully or partially self-driving vehicles; Downloadable software for perception and decision making for for fully or partially self-driving vehicles; Downloadable computer software for artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning. Non-downloadable software for advanced driving assistance systems; Non-downloadable software for fully or partially self-driving vehicles; Non-downloadable software for vehicle localization, perception and decision making for for fully or partially self-driving vehicles; Non-downloadable computer software for artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning; Scientific research and advanced product research and development services in the field of artificial intelligence; Scientific research and advanced product research and development services in the field of driver assistance for fully or partially self-driving vehicles; Software as a service (SAAS) featuring computer software for driver assistance, vehicle localization, or fully or partially self-driving vehicles.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for fully or partially self-driving vehicles; Downloadable software having specialized agents providing end-to-end solutions to narrow driving scenarios for fully or partially self-driving vehicles; Downloadable software for vehicle localization, perception and decision making for fully or partially self-driving vehicles; Downloadable computer software for artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning. Non-downloadable software for advanced driving assistance systems; Non-downloadable software for fully or partially self-driving vehicles; Non-downloadable software for perception and decision making for for fully or partially self-driving vehicles; Non-downloadable computer software for artificial intelligence, machine learning, deep learning, and supervised and unsupervised learning; Software as a service (SAAS) featuring computer software for fully or partially self-driving vehicles, vehicle localization, or advanced driving assistance systems; Platform as a service (PAAS) featuring computer software platforms for design and development of computer software having specialized agents providing end to end solutions to narrow driving scenarios for fully or partially self-driving vehicles, vehicle localization, or advanced driving assistance systems.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for advanced driving assistance systems; Downloadable software for operating fully or partially self-driving vehicles; Downloadable software for perception and decision making for fully or partially self-driving vehicles; Downloadable computer software utilizing artificial intelligence for machine learning, deep machine learning, and supervised and unsupervised machine learning Providing online, non-downloadable software for advanced driving assistance systems; Providing online, non-downloadable software for operating fully or partially self-driving vehicles; Providing online, non-downloadable software for vehicle localization, perception and decision making for fully or partially self-driving vehicles; Providing online, non-downloadable computer software utilizing artificial intelligence for machine learning, deep machine learning, and supervised and unsupervised machine learning; Scientific research and advanced product research and development services in the field of artificial intelligence; Scientific research and advanced product research and development services in the field of driver assistance for fully or partially self-driving vehicles; Software as a service (SAAS) featuring computer software for driver assistance, vehicle localization, for fully or partially self-driving vehicles
89.
Automatically identifying faulty signatures for autonomous driving applications
A method for automatically identifying faulty signatures for autonomous driving applications, the method includes receiving, by a processing circuit, a signature; matching the signature to a group of first signatures that are untagged and are randomly obtained; identifying, based on the matching, first top matching signatures; matching the signature to a group of second signatures that are untagged and are correctly or erroneously indicative of a detection of reference elements; identifying, based on the matching of the signature to the second group of second signatures, second top matching signatures; determining an overlap between the first top matching signatures and the second top matching signatures; and determining whether the signature is faulty or faultless based on the overlap.
A method for lane detection, including A computer implemented method for lane detection, the method includes (a) receiving, at one or more processing circuits of a vehicle, a plurality of initial lane boundary estimates that represent lane boundaries within a road environment, the plurality of initial lane boundary estimates include (i) first lane boundary estimates and (ii) single-image based lane boundary estimates; wherein under one or more predefined conditions the single-image based lane boundary estimates are sent once per multiple images; and (a) generating, by the one or more processing circuits, real-world lane detection estimates based on the initial lane boundary estimates, the generating includes evaluating real-world distances between initial lane boundary estimates of the lane boundaries, the initial lane boundary estimates are associated with a same point of time.
A method that is computer implemented and for segmentation-based generation of bounding shapes, the method includes (i) obtaining a bounding shape that bounds an object captured in a sensed information unit; (ii) generating a cropped image in correspondence with the bounding shape; (iii) segmenting the cropped image to a cropped image background and a cropped image foreground; and (iv) generating an updated bounding shape in correspondence with the cropped image, using the segmentation, the updated bounding shape surrounding the cropped image foreground of the cropped image.
G06T 7/70 - Determining position or orientation of objects or cameras
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/56 - Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
92.
Prediction of pedestrian entering the drivable space
A method for unregulated pedestrian step down (PSD) alert, the method may include (i) receiving, by a vehicle computerized system, a unregulated PSD indicators that are indicative of unregulated PSD situations; (ii) obtaining sensed information regarding an environment of the vehicle; (iii) processing the sensed information, wherein the processing comprises searching for at least one of the unregulated PSD indicators; and (iv) autonomously determining, when finding the at least one of the unregulated PSD identifiers, that the vehicle is approaching a situation in which a pedestrian is expected to step down into a drivable space within the environment of the vehicle. Wherein the autonomously determining triggering a response to the finding, the response is an immediate response and is executed by at least the vehicle computerized system.
A method for generating a sparse representation of a group of neural network features, the method includes (i) obtaining a group of neural network features (NNFs); and (ii) generating a lossless and sparse representation of the group of NNF, wherein the generating includes: (a) determining, by an allocation unit and based on one or more attributes of the group of NNFs, one or more relevant sparse representation generators (SRGs) out of a set of SRGs; (b) generating, by the one or more relevant SRGs, one or more relevant sparse outputs; (c) processing the one or more relevant sparse outputs to provide the lossless and sparse representation of the group of NNFs; and (d) outputting the lossless and sparse representation of the group of NNFs.
A method for motorcycle roll angle robust object detection, the method includes receiving, by a processing circuit, an image of an environment of the vehicle, wherein the image was obtained by a camera associated with a motorcycle; and generating, by the processing circuit, a signature of the image; finding, by the processing circuit, using the generated signature, a matching concept data structure out of multiple concept data structures; wherein the multiple concept data structure represents images acquired at multiple roll angles of a field of view of the camera; and detecting, by the processing circuit, within the image, an object or a scenario that is associated with the matching concept data structure.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G06T 3/60 - Rotation of whole images or parts thereof
G06T 7/70 - Determining position or orientation of objects or cameras
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
95.
Performing a driving related operation based on aerial images and sensed environment information such as radar sensed environment information
A method for driving related applications based on aerial images. The method includes (i) determining, by a processor, based on aerial map segment information and sensed environmental information, a driving control action in association the vehicle within at least the environment of the location estimate of the vehicle; (ii) determining, based on the sensed environmental information and according to the aerial map segment information, whether to perform the driving related operation within at least the environment of the location estimate of the vehicle; and (iii) responsive to determining the performance of the driving related operation, outputting information regarding the driving related operation to a control system of the vehicle.
A method for driving policy visualization, the method includes (i) receiving, by a processing circuit, perception information that comprises environmental information about an environment of a vehicle and kinematic information regarding a movement of the vehicle; (ii) receiving, by the processing circuit, a multidimensional virtual force field representation of a driving policy applicable to the vehicle; (iii) reducing a dimension of the multidimensional virtual force field representation, based on the received perception information, to produce a reduced dimensional virtual force field representation that conforms with a driving of the vehicle; and (iv) dynamically visualizing, by applying the reduced dimensional virtual force field representation, the driving policy in the driving of the vehicle.
A method for localized driving, the method includes (a) obtaining information about locations that are associated with multi-domain identifiers (MDIs) statistics, MDIs of each location are indicative of elements affecting a vehicle at the location; (b) obtaining an expected local path of a vehicle; (c) identifying path related locations, by a processing circuit, based on the expected local path and the information about the locations; and (d) determining, by the processing circuit, expected local path MDIs statistics for use in at least partially autonomous driving of a vehicle through the expected local path.
B60W 60/00 - Drive control systems specially adapted for autonomous road vehicles
B60W 40/02 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to ambient conditions
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
A method for overcoming a detection limitation of a neural network, the method includes obtaining a sensed information unit that captures an object; obtaining an indication for a detection limitation of the neural network with respect to the object, wherein the detection limitation of the neural network prevents the neural network from generating a neural network output that is indicative of the object with at least a desirable certainty; feeding the sensed information unit to the neural network to provide a neural network output; and controlling a detection of the object by the neural network based on an indication that the object is captured in the sensed information unit.
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
B60W 30/00 - Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
A method for off road driving, the method may include obtaining environment sensed information about an environment of a vehicle of a certain model, by one of more vehicle sensors of the vehicle and while driving over an off road path; detecting, by a machine learning process, an off road driving event; determining, by the machine learning process, a characteristic behavior of vehicles of the certain model when facing the off road driving event; and responding, at least in part by the machine learning process, to the occurrence of the off road driving event.
B60W 50/14 - Means for informing the driver, warning the driver or prompting a driver intervention
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
A method that is computer implemented and for accuracy for object detection, the method includes (i) receiving content from an information source located outside of a vehicle; (ii) obtaining object information regarding one or more objects located within an environment of the vehicle; and (iii) generating, by applying one or more machine learning models, one or more object related estimations for use in a detection of the one or more objects; wherein at least one of the obtaining and the generating is impacted by the content.
G06V 20/58 - Recognition of moving objects or obstacles, e.g. vehicles or pedestriansRecognition of traffic objects, e.g. traffic signs, traffic lights or roads
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
G01S 13/93 - Radar or analogous systems, specially adapted for specific applications for anti-collision purposes
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 10/98 - Detection or correction of errors, e.g. by rescanning the pattern or by human interventionEvaluation of the quality of the acquired patterns
G08G 1/0967 - Systems involving transmission of highway information, e.g. weather, speed limits
H04W 4/40 - Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
