用于估计接管时间的系统和方法
By training action-time and recovery-time networks and combining them with a driver monitoring system, the driver takeover time is dynamically estimated and updated, solving the problem of takeover time estimation in ODD departure events of autonomous driving systems and improving the safety and reliability of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 哲内提
- Filing Date
- 2021-05-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing autonomous driving systems cannot effectively estimate the time required for driver takeover when switching from autonomous to manual driving, leading to safety and reliability issues.
The driver takeover time is estimated by training the Action Time Network (ATN) and Recovery Time Network (RTN). The driver state parameters are obtained by combining the driver monitoring system (DMS). The Action Time Network outputs the time required to process the ODD departure event, and the Recovery Time Network outputs the time required for the driver to reach an attention threshold. The control circuit performs comprehensive judgment and updates.
It enables dynamic estimation and updating of driver takeover time, improving the safety and reliability of the autonomous driving system in ODD departure events and ensuring that the driver can take over vehicle control in a timely and safe manner.
Smart Images
Figure CN113734193B_ABST