Agent importance prediction for autonomous driving
AssigneeMotional AD LLC
InventorsChristopher Hazard, Akshay Bhagat, Balarama Raju Buddharaju, Zhongtao Liu, Yunming Shao, Lu Lu, Sammy Omari, Henggang Cui
Life of this patent
Estimating the term…
Abstract
A method, a system, and a non-transitory storage media for determining agent importance prediction for autonomous driving. Input features associated with agents present in an environment surrounding a vehicle are processed. Output features associated with the agents are determined based on the input features. An importance of each agent is predicted using the output features. One or more movements of the vehicle are determined based on the predicted agent importance.
Claims20
A system, comprising:
- at least one sensing device configured to detect one or more input features associated with one or more agents in a plurality of agents present in an environment surrounding a vehicle, and
- a vehicle controller comprising at least one processor and at least one non-transitory storage media storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
- processing, using at least one processor, the one or more input features associated with the one or more agents in the plurality of agents present in the environment surrounding the vehicle;
- determining, using the at least one processor, one or more output features associated with the one or more agents based on the one or more input features;
- predicting, using the at least one processor, an importance score of each agent in the one or more agents based on the one or more output features by iteratively determining correlations between predicted trajectories of the vehicle and respective agents when removed from a scene;
- determining, using the at least one processor, based on the importance score of each agent in the one or more agents, one or more movements of the vehicle;
- and
- executing the one or more movements by the vehicle.
A method comprising:
- processing, using at least one processor, one or more input features associated with one or more agents in a plurality of agents present in an environment surrounding a vehicle;
- determining, using the at least one processor, one or more output features associated with the one or more agents based on the one or more input features;
- predicting, using the at least one processor, an importance score of each agent in the one or more agents based on the one or more output features by iteratively determining correlations between predicted trajectories of the vehicle and respective agents when removed from a scene;
- determining, using the at least one processor, based on the importance score of each agent in the one or more agents, one or more movements of the vehicle;
- and
- executing the one or more movements by the vehicle.
At least one non-transitory storage media storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
- processing, using at least one processor, one or more input features associated with one or more agents in a plurality of agents present in an environment surrounding a vehicle;
- determining, using the at least one processor, one or more output features associated with the one or more agents based on the one or more input features;
- predicting, using the at least one processor, an importance score of each agent in the one or more agents based on the one or more output features by iteratively determining correlations between predicted trajectories of the vehicle and respective agents when removed from a scene;
- determining, using the at least one processor, based on the importance score of each agent in the one or more agents, one or more movements of the vehicle;
- and
- executing the one or more movements by the vehicle.
Dependencies are inferred from the claim text.