Motion-Plan Validator for Autonomous Vehicle
AssigneeUber Technologies, Inc.
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:
- receiving, by a computing system comprising one or more computing devices and from a motion-planning system of an autonomous vehicle, data indicating a motion plan of the autonomous vehicle through an environment of the autonomous vehicle;
- receiving, by the computing system, data indicating one or more inputs utilized by the motion-planning system in generating the motion plan;
- and
- determining, by a plan validator of the computing system and based at least in part on the data indicating the motion plan and the data indicating the one or more inputs, whether execution of the motion plan by the autonomous vehicle would violate one or more predetermined constraints applicable to the motion plan of the autonomous vehicle, the plan validator being separate and distinct from the motion-planning system.
A system comprising:
- one or more processors;
- and
- a memory storing instructions that when executed by the one or more processors cause the system to perform operations comprising:
- generating, by a motion-planning system of an autonomous vehicle, using a machine-learning model, and based at least in part on one or more inputs, a motion plan of the autonomous vehicle through an environment of the autonomous vehicle;
- determining, by a plan validator of the autonomous vehicle and based at least in part on the motion plan and the one or more inputs, whether execution of the motion plan by the autonomous vehicle would violate one or more predetermined constraints applicable to the motion plan of the autonomous vehicle, the plan validator being separate and distinct from the motion-planning system;
- and
- determining, based at least in part on whether execution of the motion plan by the autonomous vehicle would violate the one or more predetermined constraints, whether to execute the motion plan.
An autonomous vehicle comprising:
- one or more sensors configured to generate data describing an environment of the autonomous vehicle;
- one or more vehicle controls configured to operate the autonomous vehicle;
- a motion-planning system;
- a plan validator separate and distinct from the motion-planning system;
- one or more processors;
- and
- a memory storing instructions that when executed by the one or more processors cause:
- the motion-planning system to generate, using a machine-learning model and based at least in part on one or more inputs determined based at least in part on data generated by the one or more sensors, a motion plan of the autonomous vehicle through the environment;
- the plan validator to determine, based at least in part on the motion plan and the one or more inputs, whether execution of the motion plan by the autonomous vehicle would violate one or more predetermined constraints applicable to motion the motion plan of the autonomous vehicle;
- and
- the autonomous vehicle to determine, based at least in part on whether execution of the motion plan by the autonomous vehicle would violate the one or more predetermined constraints, whether to interface with the one or more vehicle controls to execute the motion plan.
Dependencies are inferred from the claim text.