Abstract: An autonomous vehicle navigates an environment in which occlusions block the vehicle's ability to detect moving objects. The vehicle handles this by receiving sensor data corresponding to the environment, identifying one or more particles of a plurality of initialized particles that have a non-zero probability of being associated with a potential occluded actor in the occluded region, and generating a trajectory of the autonomous vehicle for traversing the environment based on spatiotemporal reasoning about the occluded region and taking into account the one or more particles. Each particle may be associated with a potential actor.

Abstract: Disclosed herein are systems, methods, and computer program products for vehicle path planning. The methods comprise: estimating a current state of a vehicle based on sensor data; generating a control error representing a difference between the estimated current state of the vehicle and a desired state of the vehicle as described by a previously published trajectory; comparing the control error to a threshold value; generating a first plan for the vehicle using an open-loop path planning approach when the control error is below the threshold value or a second plan for the vehicle using a closed-loop path planning approach when the control error is above the threshold value; and causing the vehicle to execute the first or second plan.

Abstract: Systems and methods for controlling navigation of an autonomous vehicle through an intersection are disclosed. The methods include determining a loiter pose of an autonomous vehicle for stopping at a point within the intersection before initiating an unprotected turn for traversing the intersection. One or more distinct classes of trajectories are then identified, each of which is associated with multiple trajectories that take the same combination of discrete actions with respect to the loiter pose. A constraint set for each of the one or more distinct classes of trajectories is then be computed based on the loiter pose, and a candidate trajectory is determined for each of the one or more distinct classes based on the corresponding constraint set. A trajectory for the autonomous vehicle for executing the unprotected turn for traversing the intersection is selected from amongst the candidate trajectories.

Abstract: A driving system for the automated driving for a motor vehicle is configured to determine a field of vision of at least one sensor of the motor vehicle, for at least one area in the surroundings of the motor vehicle which does not lie in the field of vision of the at least one sensor, to simulate, if appropriate, a virtual road user in the at least one area in the surroundings of the motor vehicle, to carry out an evaluation of action options in accordance with a possible virtual collision of the motor vehicle with the at least one virtual road user, to select one of these action options in accordance with the above, and to execute the selected action option.