Abstract: 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.

Abstract: A method for communicating with a driver of a vehicle, the method includes (i) obtaining object information regarding one or more objects located within an environment of the vehicle; (ii) analyzing the object information; (iii) determining, by using one or more neural network (NNs), and based on the object information, a virtual force associated with a physical model and representing an impact of the one or more objects on a behavior of the vehicle; and (iv) determining, based on at least the virtual force, a force feedback for use in providing a physical restraining force to be applied in association with a driver action made by the driver using the vehicle.

Abstract: A method for bypass alert, the method includes (i) obtaining sensed information about an environment of the vehicle, by one of more vehicle sensors of a vehicle. The environment of the vehicle includes a passing lane and a current lane; (ii) determining whether a driver initiates a bypass of another vehicle to be bypassed, by a first machine learning process (MLP), based on at least one out of vehicle parameters and the sensed information (iii) determining that the vehicle entered the passing lane; (iv) determining, by a second (MLP), a determined time to collision (TTC) to an incoming vehicle that is located at the passing lane and drives towards the vehicle; (v) determining, based on at least on the determined TTC and an allowable TTC to provide a safety parameter of the bypass; and (vi) responding to the safety parameter.

Abstract: A method for providing an in-vehicle indication, the method may include obtaining, during a driving session of a vehicle, external audio information about audio generated outside the vehicle; determining whether the audio generated outside the vehicle comprises driving affecting audio; and generating the in-vehicle indication, within the vehicle, when determining that the audio generated outside comprises driving affecting audio. The in-vehicle indication is indicative about the driving affecting audio generated outside the vehicle.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method for intersection assistance, the method may include obtaining sensed information regarding an environment of the vehicle; determining an occurrence of an intersection related situation, based on the sensed information; generating one or more intersection driving related decisions; wherein the generating comprises processing, by one or more narrow AI agents of a group of narrow AI agents, at least one out of (a) at least a first part of the sensed information, and (b) an outcome of a pre-processing of at least a second part of the sensed information; and responding to the one or more intersection driving related decisions; wherein the responding comprises at least one out of (a) executing the one or more intersection driving related decisions, and (b) suggesting executing the one or more intersection driving related decisions.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.