Prediction-based system and method for trajectory planning of autonomous vehicles

US10782694B2 · kind B2 · utility

Assignee

• TUSIMPLE, INC. · US

Inventors

• Xiaomin Zhang · Charlotte, US
• Yilun Chen · San Diego, US
• Guangyu Li · Portland, US
• Xing Sun · San Diego, US
• Wutu Lin · San Diego, US
• Liu Liu · San Diego, US
• Kai-Chieh Ma · San Diego, US
• Zijie Xuan · Kino, US
• Yufei Zhao · San Diego, US

Key dates

• Filing date: Nov 7, 2017
• Grant date: Sep 22, 2020
• Expiry date: Aug 30, 2038

Classification

• Technology area (CPC G): Physics
• CPC primary: G08G1/167
• WIPO field: Control
• WIPO sector: Instruments

Abstract

A prediction-based system and method for trajectory planning of autonomous vehicles are disclosed. A particular embodiment is configured to: receive training data and ground truth data from a training data collection system, the training data including perception data and context data corresponding to human driving behaviors; perform a training phase for training a trajectory prediction module using the training data; receive perception data associated with a host vehicle; and perform an operational phase for extracting host vehicle feature data and proximate vehicle context data from the perception data, generating a proposed trajectory for the host vehicle, using the trained trajectory prediction module to generate predicted trajectories for each of one or more proximate vehicles near the host vehicle based on the proposed host vehicle trajectory, determining if the proposed trajectory for the host vehicle will conflict with any of the predicted trajectories of the proximate vehicles, and modifying the proposed trajectory for the host vehicle until conflicts are eliminated.