A method is disclosed for evaluating a classifier used to determine a traffic light signal state in images. The method includes, by a computer vision system of a vehicle, receiving at least one image of a traffic signal device of an imminent intersection. The traffic signal device includes a traffic signal face including one or more traffic signal elements. The method includes classifying, by a traffic light classifier (TLC), a classification state of the traffic signal face using labeled images correlated to the received at least one image. The classification state controls an operation of the vehicle at the intersection. The method includes evaluating a performance of the classifying of the classification state generated by the TLC. The evaluation is a label-free performance evaluation based on unlabeled images. The method includes training the TLC based on the evaluated performance.

A method for traffic light auto-labeling includes aggregating vehicle-to-infrastructure (V2I) traffic light signals at an intersection to determine transition states of each driving lane at the intersection during operation of an ego vehicle. The method also includes automatically labeling image training data to form auto-labeled image training data for a traffic light recognition model within the ego vehicle according to the determined transition states of each driving lane at the intersection. The method further includes planning a trajectory of the ego vehicle to comply with a right-of-way according to the determined transition states of each driving lane at the intersection according to a trained traffic light detection model. A federated learning module may train the traffic light recognition model using the auto-labeled image training data during the operation of the ego vehicle.

Aspects of the disclosure provide for generating distributions for hypothetical or potentially occluded objects. For instance, a location for which to generate one or more distributions may be identified. Observations of road users by perception systems of a plurality of autonomous vehicles may be accessed. Each of these observations may identify a characteristic of one of the road users. A distribution of the characteristic for the location may be determined based on the observations. The distribution may be provided to one or more autonomous vehicles in order to enable the one or more autonomous vehicles to use the distribution to generate a characteristic for a hypothetical occluded road user and to respond to the hypothetical occluded road user.

A deceleration assistance device including: a target information acquisition unit for acquiring information of a target located in front of a vehicle; a position estimation unit for estimating an estimated position of a deceleration object; a position recognition unit for recognizing a position of the deceleration object; and a control unit for executing, based on the estimated position, first deceleration control of decelerating a vehicle at a first deceleration and executing, based on the recognized position, second deceleration control of decelerating the vehicle at a second deceleration. The control unit executes processing of gradually changing a deceleration of the vehicle from the first deceleration toward the second deceleration when the deceleration control is caused to transition from the first to the second deceleration control, and when a difference exists between the first and second deceleration.

A graph representation of a tactical map representing a plurality of static components of an environment of a vehicle is generated. Nodes of the graph represent static components, and edges represent relationships between multiple static components. Different edge types are used to indicate respective relationship semantics among the static components. Individual nodes are represented as having the same number and types of edges in the graph. Using the graph as input to a neural network based model, a set of results is obtained. A motion control directive based at least in part on the results is transmitted to a motion-control subsystem of the vehicle.

A vehicle cruise control method and apparatus related to the technical field of vehicle manufacturing are provided. The method resolves a problem of relatively large energy consumption during vehicle cruise control.

Driver safety, vehicle safety, and environment safety may be scored based on a variety of input data concerning a driver, a vehicle, or an environment in which the vehicle drives. An overall safety score may be generated based on at least some of these three scores. These scores may be compared to thresholds to trigger or initiate actions such as providing notifications to drivers, raising or reducing vehicle insurance rates, providing coupons and promotions to drivers, or limiting vehicle speed in a manner that is personalized to the driver and/or vehicle and/or environment.

A hybrid vehicle includes an engine, a drive motor selectively operated as a generator to generate electrical energy; a battery charged with the electrical energy generated in the drive motor; a navigation device determining a travelling path of the hybrid vehicle from a departure of the hybrid vehicle to a destination of the hybrid vehicle and an expected vehicle speed of the travelling path; and a controller which divides an entire travelling path of the hybrid vehicle expected by the navigation device into one or more travelling sections based on the travelling information, determines an average vehicle speed of each travelling section, an average vehicle speed of the entire travelling path, and travelling energy of the vehicle in each travelling section, determines an expected State Of Charge (SOC) profile of the battery based on the travelling energy, and determines a charge mode of the battery based on the average vehicle speed and an initial SOC value of the expected SOC profile.

A method of autonomous vehicle control, comprising: receiving an image of a lenticular human-imperceptible marker embedded in an element of an environment that an autonomous vehicle is moving in, the marker having a pattern usable for determining positional data of the moving vehicle, the image captured using human-invisible light, analyzing the received image of the human-imperceptible marker, and controlling the autonomous vehicle based on the analyzed image of the human-imperceptible marker.

This application is directed to augmenting training data used for vehicle driving modelling. A computer system obtains a first image of a road and identifies a drivable area of the road within the first image. The computer system obtains an image of an object and generates a second image from the first image by overlaying the image of the object over the drivable area. The second image is added to a corpus of training images to be used by a machine learning system to generate a model for facilitating driving of a vehicle (e.g., at least partial autonomously). In some embodiments, the computer system applies machine learning to train a model using the corpus of training images and distributes the model to one or more vehicles. In use, the model processes road images captured by the one or more vehicles to facilitate vehicle driving.