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 vehicle trajectory prediction device is provided. The vehicle trajectory prediction device includes a transceiver, at least one processor, and at least one memory operatively connected with the at least one processor to store at least one instruction causing the at least one processor to perform operations. The operations receive first trajectory data for an ego-vehicle and second trajectory data for at least one neighbor-vehicle, obtain a first feature vector from a first extractor and obtain a second feature vector from a second extractor, obtain an interdependency feature vector between the ego-vehicle and the at least one neighbor-vehicle from a third extractor having mapping data generated by mapping the second feature vector to the second trajectory data as input data, and generate predicted trajectory data of the ego-vehicle from a trajectory generator having the first feature vector and the interdependency feature vector as input data.

An apparatus includes processing circuitry configured to determine an actual driving performance of a driver in a manual driving mode and a projected driving performance if the vehicle had been operated in an autonomous driving mode, compare the driving performance in the manual driving mode and the autonomous driving mode, and transmit a feedback to the driver based on the comparison. The processing circuitry can be further configured to determine a driver state of the driver in the manual driving mode, determine environmental driving condition of the vehicle, and establish a baseline behavior of the driver as a function of the driver state and the environmental driving condition.

Methods for reversing determination for a vehicle asset are provided. The methods include capturing by a telematics device coupled to the vehicle acceleration data from a three-axis accelerometer, determining by an edge reversing-determination machine learning mode, a machine-learning-determined reversing indication for the vehicle asset. The edge reversing-determination machine-learning model being updated based on a centralized reversing-determination machine-learning model trained using a vehicle-provided reversing indication.

An apparatus for controlling backward driving of a vehicle including: a driving trajectory generation unit configured to generate a driving trajectory for backward driving of an ego vehicle on a target path, using sensing information acquired while the ego vehicle drives forward along the target path; and a control unit configured to control the backward driving of the ego vehicle on the target path according to the driving trajectory generated by the driving trajectory generation unit, correct the driving trajectory using driving information of another vehicle, which has driven backward on the target path before the ego vehicle, when a change on the target path is sensed in comparison to during the forward driving of the ego vehicle during the process of controlling the backward driving of the ego vehicle, and control the backward driving of the ego vehicle according to the corrected driving trajectory.

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a method for navigating a user vehicle may include acquiring, using at least one image capture device, a plurality of images of an area in a vicinity of the user vehicle; determining from the plurality of images a first lane constraint on a first side of the user vehicle and a second lane constraint on a second side of the user vehicle opposite to the first side of the user vehicle; enabling the user vehicle to pass a target vehicle if the target vehicle is determined to be in a lane different from the lane in which the user vehicle is traveling; and causing the user vehicle to abort the pass before completion of the pass, if the target vehicle is determined to be entering the lane in which the user vehicle is traveling.

A method and apparatus for determining a turn-round path of a vehicle, a device and a storage medium are provided. An embodiment of the method includes: determining a starting position and a target position for the vehicle to turn round on a road; determining, based at least partially on road information associated with the road and vehicle information associated with the vehicle, a candidate turn-round path between the starting position and the target position; evaluating the feasibility of the candidate turn-round path; and determining, based on the evaluation on the feasibility, a turn-round path by which the vehicle is to turn round on the road.

A method and an apparatus for generating a route planning model and a storage medium are provided. The method for generating a route planning model includes: obtaining a target route data set associated with a target site; and determining a target route planning model of the target site with a site optimization object corresponding to the target site, based on the target route data set and a first route planning model; wherein the first route planning model is determined based on a set of historical route data through at least a first training, the set of historical route data being associated with a plurality of sites different from the target site and a first training optimization object for the first training corresponding to the plurality of sites.

Jaywalking behaviors of vulnerable road users (VRUs) such as cyclists or pedestrians can be predicted. Location data is obtained that identifies a location of a VRU within a vicinity of a vehicle. Environmental data is obtained that describes an environment of the VRU, where the environmental data identifies a set of environmental features in the environment of the VRU. The system can determine a nominal heading of the VRU, and generate a set of predictive inputs that indicate, for each of at least a subset of the set of environmental features, a physical relationship between the VRU and the environmental feature. The physical relationship can be determined with respect to the nominal heading of the VRU and the location of the VRU. The set of predictive inputs can be processed with a heading estimation model to generate a predicted heading offset (e.g., a target heading offset) for the VRU.

A method for predicting a future action of an object for a driving assistance system for a highly automated mobile vehicle. At least one sensor signal from at least one vehicle sensor of the vehicle is read in, the sensor signal representing at least one piece of kinematic object information concerning the object that is detected by the vehicle sensor at an instantaneous point in time. A planner signal from a planner of the autonomous driving assistance system is read in, the planner signal representing at least one piece of semantic information concerning the object or the surroundings of the object at a point in time in the past. The kinematic object information is fused with the semantic information to obtain a fusion signal. A prediction signal is determined using the fusion signal, the prediction signal representing the future action of the object.