Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

Abstract: Systems and methods for vehicle motion planning based on uncertainty are provided. A method can include obtaining scene data descriptive of one or more objects within a surrounding environment of the autonomous vehicle. The method can include determining one or more subproblems based at least in part on the scene data. In some implementation, each of the one or more subproblems can correspond to at least one object within the surrounding environment of the autonomous vehicle. The method can include generating one or more branching policies based at least in part on the one or more subproblems. In some implementations, each of the one or more branching policies can include scene data associated with the autonomous vehicle and one or more objects within the surrounding environment of the autonomous vehicle. The method can include determining one or more costs associated each of the one or more branching policies.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can generate constraints based on where objects of interest are predicted to be relative to an autonomous vehicle. A constraint solver can identify navigation decisions for each of the constraints that provide a consistent solution across all constraints. The solution provided by the constraint solver can be in the form of a trajectory path determined relative to constraint areas for all objects of interest. The trajectory path represents a set of navigation decisions such that a navigation decision relative to one constraint doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints.

Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can generate constraints based on where objects of interest are predicted to be relative to an autonomous vehicle. A constraint solver can identify navigation decisions for each of the constraints that provide a consistent solution across all constraints. The solution provided by the constraint solver can be in the form of a trajectory path determined relative to constraint areas for all objects of interest. The trajectory path represents a set of navigation decisions such that a navigation decision relative to one constraint doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints.

Abstract: Generally, the present disclosure is directed to systems and methods that include or otherwise leverage a decision point engine as part of determining a motion plan for an autonomous vehicle. In particular, a motion planning system that includes a decision point engine can be configured to obtain object data associated with one or more objects identified near one or more travel paths of an autonomous vehicle. The system can determine a stopping profile based at least in part on the object data, wherein the stopping profile identifies a set of candidate states for the autonomous vehicle that preserves an ability of the autonomous vehicle to stop before the interaction point. The system can determine a decision point corresponding to a selected state from the set of candidate states identified by the stopping profile, and determine a trajectory for the autonomous vehicle based at least in part on the decision point.

Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance traveled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

Abstract: Systems and methods for vehicle motion planning based on uncertainty are provided. A method can include obtaining scene data descriptive of one or more objects within a surrounding environment of the autonomous vehicle. The method can include determining one or more subproblems based at least in part on the scene data. In some implementation, each of the one or more subproblems can correspond to at least one object within the surrounding environment of the autonomous vehicle. The method can include generating one or more branching policies based at least in part on the one or more subproblems. In some implementations, each of the one or more branching policies can include scene data associated with the autonomous vehicle and one or more objects within the surrounding environment of the autonomous vehicle. The method can include determining one or more costs associated each of the one or more branching policies.

Abstract: Generally, the present disclosure is directed to systems and methods that include or otherwise leverage a decision point engine as part of determining a motion plan for an autonomous vehicle. In particular, a motion planning system that includes a decision point engine can be configured to obtain object data associated with one or more objects identified near one or more travel paths of an autonomous vehicle. The system can determine a stopping profile based at least in part on the object data, wherein the stopping profile identifies a set of candidate states for the autonomous vehicle that preserves an ability of the autonomous vehicle to stop before the interaction point. The system can determine a decision point corresponding to a selected state from the set of candidate states identified by the stopping profile, and determine a trajectory for the autonomous vehicle based at least in part on the decision point.

Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance traveled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a constraint solver determines a multi-dimensional space for each phase of a plurality of different phases of a lane change maneuver. For each different phase, objects of interest interacting with first and second lanes of the nominal path can be determined and constraints can be respectively generated. A portion of the multi-dimensional space including corresponding constraints that applies to a respective timeframe associated with each phase can be determined. The respective portions of the multi-dimensional space including corresponding constraints for each phase of the plurality of different phases of the lane change maneuver can be combined to generate a multiplexed space through which a low-cost trajectory path can be determined.

Abstract: The present disclosure provides autonomous vehicle systems and methods that include or otherwise leverage a motion planning system that generates constraints as part of determining a motion plan for an autonomous vehicle (AV). In particular, a scenario generator within a motion planning system can generate constraints based on where objects of interest are predicted to be relative to an autonomous vehicle. A constraint solver can identify navigation decisions for each of the constraints that provide a consistent solution across all constraints. The solution provided. by the constraint solver can be in the form of a trajectory path determined relative to constraint areas for all objects of interest. The trajectory path represents a set of navigation decisions such that a navigation decision relative to one constraint doesn't sacrifice an ability to satisfy a different navigation decision relative to one or more other constraints.

Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.

Abstract: Systems and methods are directed to providing speed limit context awareness during operation of an autonomous vehicle. In one example, a computer-implemented method for applying speed limit context awareness in autonomous vehicle operation includes obtaining, by a computing system comprising one or more computing devices, a plurality of features descriptive of a context and a state of an autonomous vehicle. The method further includes determining, by the computing system, a context response for the autonomous vehicle based at least in part on a machine-learned model and the plurality of features, wherein the context response includes a derived speed constraint for the autonomous vehicle. The method further includes providing, by the computing system, the context response to a motion planning application of the autonomous vehicle to determine a motion plan for the autonomous vehicle.

Abstract: The present disclosure provides systems and methods that control the motion of an autonomous vehicle by rewarding or otherwise encouraging progress toward a goal, rather than simply rewarding distance travelled. In particular, the systems and methods of the present disclosure can project a candidate motion plan that describes a proposed motion path for the autonomous vehicle onto a nominal pathway to determine a projected distance associated with the candidate motion plan. The systems and methods of the present disclosure can use the projected distance to evaluate a reward function that provides a reward that is positively correlated to the magnitude of the projected distance. The motion of the vehicle can be controlled based on the reward value provided by the reward function. For example, the candidate motion plan can be selected for implementation or revised based at least in part on the determined reward value.