Back to results
US 11,899,462 B2Granted
Motion-plan validator for autonomous vehicle
AssigneeUatc, LLC
InventorsMoslem Kazemi, Anthony Joseph Stentz
Life of this patent
Estimating the term…
Abstract
The present disclosure is directed to validating motion plans for autonomous vehicles. In particular, the methods, devices, and systems of the present disclosure can: receive data indicating a motion plan of an autonomous vehicle through an environment of the autonomous vehicle; receive data indicating one or more inputs utilized in generating the motion plan; and determine, based at least in part on the data indicating the motion plan and the data indicating the input(s), whether execution of the motion plan by the autonomous vehicle would violate one or more predetermined constraints applicable to motion plans for the autonomous vehicle.
Claims20
A computer-implemented method comprising:
- generating, using a plan generator configured to generate motion plans for an autonomous vehicle, and based at least in part on one or more inputs associated with a surrounding environment, data indicating a plurality of motion plans of the autonomous vehicle, wherein the plurality of motion plans are respectively associated with a plurality of trajectories of the autonomous vehicle through an environment of the autonomous vehicle, wherein the one or more inputs comprise object data generated by a perception system of the autonomous vehicle;
- selecting a motion plan of the plurality of motion plans for execution by the autonomous vehicle;
- based at least in part on the selection of the motion plan, processing, using a plan validator configured to validate motion plans for the autonomous vehicle, the data indicating the selected motion plan and the data indicating the one or more inputs, to determine whether execution of the motion plan by the autonomous vehicle would violate one or more constraints applicable to the selected motion plan;
- and
- responsive to a determination that execution of the motion plan by the autonomous vehicle would violate at least one constraint of the one or more constraints:
- determining one or more aspects of one or more cost functions associated with violation of the at least one constraint and
- generating, using a machine-learned model, a new motion plan for the autonomous vehicle based at least in part on the one or more aspects.
4 more elements
An autonomous vehicle control system for an autonomous vehicle, the autonomous vehicle control system comprising:
- one or more processors;
- one or more non-transitory computer-readable media that store instructions that are executable by the one or more processors to cause the autonomous vehicle control system to perform operations, the operations comprising:
- generating, using a plan generator configured to generate motion plans for the autonomous vehicle, and based at least in part on one or more inputs associated with a surrounding environment, data indicating a plurality of motion plans of an autonomous vehicle, wherein the plurality of motion plans are respectively associated with a plurality of trajectories of the autonomous vehicle through an environment of the autonomous vehicle, wherein the one or more inputs comprise object data generated by a perception system of the autonomous vehicle;
- selecting a motion plan of the plurality of motion plans for execution by the autonomous vehicle;
- based at least in part on the selection of the motion plan, processing, using a plan validator configured to validate motion plans for the autonomous vehicle, the data indicating the selected motion plan and the data indicating the one or more inputs, to determine whether execution of the motion plan by the autonomous vehicle would violate one or more constraints applicable to the selected motion plan;
- and
- responsive to a determination that execution of the motion plan by the autonomous vehicle would violate at least one constraint of the one or more constraints:
- determining one or more aspects of one or more cost functions associated with violation of the at least one constraint;
- and
- generating a new motion plan for the autonomous vehicle using a machine-learning model based at least in part on the one or more aspects.
7 more elements
An autonomous vehicle, the autonomous vehicle comprising:
- one or more processors;
- one or more non-transitory computer-readable media that store instructions that are executable by the one or more processors to cause the autonomous vehicle to perform operations, the operations comprising:
- generating, using a plan generator configured to generate motion plans for the autonomous vehicle, and based at least in part on one or more inputs associated with a surrounding environment, data indicating a plurality of motion plans of an autonomous vehicle, wherein the plurality of motion plans are respectively associated with a plurality of trajectories of the autonomous vehicle through an environment of the autonomous vehicle, wherein the one or more inputs comprise object data generated by a perception system of the autonomous vehicle;
- selecting a motion plan of the plurality of motion plans for execution by the autonomous vehicle;
- based at least in part on the selection of the motion plan, processing, using a plan validator configured to validate motion plans for the autonomous vehicle, the data indicating the selected motion plan and the data indicating the one or more inputs, to determine whether execution of the motion plan by the autonomous vehicle would violate one or more constraints applicable to the selected motion plan;
- and
- responsive to a determination that execution of the motion plan by the autonomous vehicle would violate at least one constraint of the one or more constraints:
- determining one or more aspects of one or more cost functions associated with violation of the at least one constraint and
- generating a new motion plan for the autonomous vehicle using a machine-learning model based at least in part on the one or more aspects.
6 more elements
Dependencies are inferred from the claim text.