A vehicle control system and method includes obtaining a size of a vehicle system, identifying locations of different portions of the vehicle system, and determining one or more of a) whether the vehicle system is disposed within or across an intersection of routes or b) a predicted time of arrival at which the vehicle system will be disposed within or across the intersection based on the size of the vehicle system and the locations of the different portions of the vehicle system.

In one embodiment, an exemplary method includes receiving, at a simulation platform, a record file recorded by a manually-driving ADV on a road segment, the simulation platform including a first encoder, a second encoder, and a performance evaluator; simulating automatic driving operations of a dynamic model of the ADV on the road segment based on the record file, the dynamic model including an autonomous driving module to be evaluated. The method further includes: for each trajectory generated by the autonomous driving module during the simulation: extracting a corresponding trajectory associated with the manually-driving ADV from the record file, encoding the trajectory into a first semantic map and the corresponding trajectory into a second semantic map, and generating a similarity score based on the first semantic map and the second semantic map. The method also includes generating an overall performance score based on each similarity score.

A control device for controlling autonomous driving of a vehicle, the control device includes a processor and a memory storing instructions. The instructions, when executed by the processor, cause the control device to perform operations including: switching a control content in the autonomous driving of the vehicle based on a position of the vehicle.

A system, map server and method of navigating a vehicle through an intersection. The map server includes a remote processor and a communication device. The remote processor determines a first road edge for a first road entering an intersection and a second road edge for a second road entering the intersection. The remote processor constructs an intersection edge that connects a first point on the first road edge to a second point on the second road edge. The communication device communicates the intersection edge to the vehicle. A vehicle processor at the vehicle navigates the vehicle through the intersection using the intersection edge.

Systems and methods for protecting a vehicle at an intersection are disclosed herein. One embodiment detects that the vehicle is stopped at the intersection at one of a first position and a second position; detects that a driver of the vehicle is pressing on an accelerator pedal of the vehicle; delays acceleration of the vehicle automatically by a first predetermined period, when the vehicle has been detected at the first position; and delays acceleration of the vehicle automatically by a second predetermined period, when the vehicle has been detected at the second position. Delaying acceleration of the vehicle automatically prevents the vehicle from being struck by a cross-traffic vehicle that has proceeded through the intersection against a first traffic signal in a red-light state.

Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

System, methods, and other embodiments described herein relate to improving right-of-way determinations at an intersection. In one embodiment, a method includes acquire, in a lead vehicle that is a cloud leader of a micro-cloud, observations about the intersection for a set of vehicles including at least one remote vehicle. The set of vehicles are approaching the intersection. The remote vehicle and the lead vehicle are members of the micro-cloud. The method includes deriving an assignment of right-of-ways indicating an order about how the set of vehicles may proceed through the intersection. The method includes providing the assignment to at least the remote vehicle to control right-of-way at the intersection.

Provided are methods for predicting motion of hypothetical agents, which can include receiving sensor data, generating a segmentation mask indicative of at least one occluded area, generating at least one hypothetical agent trajectory, determining at least one agent generation point, determining whether a threshold distance from the at least one agent generation point to the vehicle is satisfied, generating at least one agent, planning a path of the vehicle and controlling the vehicle according to the planned path. Systems and computer program products are also provided.

Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future that meet a criterion, allowing for more efficient sampling. A predicted position of the object in the future may be determined by sampling from the distribution.

A traveling path setting method for a vehicle has a set traveling path of a host vehicle that includes a traveling path that turns across another lane at an intersection. The traveling path setting method is configured to set a traveling path for turning of the vehicle to an inner side of a turning direction when an adjacent vehicle exists within a predetermined distance outward of the traveling path of the host vehicle in the turning direction, compared to a case where no adjacent vehicle exists.