Neural network approach for parameter learning to speed up planning for complex driving scenarios

US11731612B2 · kind B2 · utility

Assignee

• BAIDU USA LLC · US

Inventors

• Jinyun Zhou · Sha Tin, CN
• Runxin He · Sunnyvale, US
• Qi Luo · Sunnyvale, US
• Jinghao Miao · Sunnyvale, US
• Jiangtao Hu · Sunnyvale, US
• Yu Wang · Sunnyvale, US
• Jiaxuan Xu · Sunnyvale, US
• Shu Jiang · Sunnyvale, US

Key dates

• Filing date: Apr 30, 2019
• Grant date: Aug 22, 2023
• Expiry date: Dec 22, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/045
• WIPO field: Transport
• WIPO sector: Mechanical engineering

Abstract

In one embodiment, a computer-implemented method of operating an autonomous driving vehicle (ADV) includes perceiving a driving environment surrounding the ADV based on sensor data obtained from one or more sensors mounted on the ADV, determining a driving scenario, in response to a driving decision based on the driving environment, applying a predetermined machine-learning model to data representing the driving environment and the driving scenario to generate a set of one or more driving parameters, and planning a trajectory to navigate the ADV using the set of the driving parameters according to the driving scenario through the driving environment.