Trajectory planning based on extracted trajectory features
AssigneeMotional AD LLC
InventorsEric McKenzie Wolff, Tung Minh Phan, Ting-Sheng Chu, Momchil Tomov
Life of this patent
Estimating the term…
Abstract
A trajectory planning system can be used to select a trajectory for an autonomous vehicle. The trajectory planning system may generate multiple trajectories and extract features from the generated trajectories. The trajectory planning system may evaluate the trajectories based on the extracted features and select a trajectory for the vehicle based on the evaluation. The selected trajectory may be used to control the vehicle.
Claims20
A method, comprising:
- obtaining scene data associated with a scene of a vehicle;
- generating a plurality of trajectories for the vehicle based on the scene data;
- extracting a plurality of features from a particular trajectory of the plurality of trajectories;
- evaluating, using a machine learning model, the particular trajectory in a trajectory space based on the plurality of features and a vehicle planning policy;
- selecting a first trajectory from the plurality of trajectories based on the evaluating the particular trajectory;
- and
- causing the vehicle to be controlled based on the first trajectory.
A system, comprising:
- a data store storing computer-executable instructions;
- and
- a processor configured to execute the computer-executable instructions, wherein execution of the computer-executable instructions causes the system to:
- obtain scene data associated with a scene of a vehicle;
- generate a plurality of trajectories for the vehicle based on the scene data;
- extract a plurality of features from a particular trajectory;
- evaluate, using a machine learning model, the particular trajectory in a trajectory space based on the plurality of features and a vehicle planning policy;
- select a first trajectory from the plurality of trajectories based on the evaluation of the particular trajectory;
- and
- cause the vehicle to be controlled based on the first trajectory.
Non-transitory computer-readable media comprising computer-executable instructions that, when executed by a computing system, causes the computing system to:
- obtain scene data associated with a scene of a vehicle;
- generate a plurality of trajectories for the vehicle based on the scene data;
- extract a plurality of features from a particular trajectory;
- evaluate, using a machine learning model, the particular trajectory in a trajectory space based on the plurality of features and a vehicle planning policy;
- select a first trajectory from the plurality of trajectories based on the evaluation of the particular trajectory;
- and
- cause the vehicle to be controlled based on the first trajectory.
Dependencies are inferred from the claim text.