一种模糊规则自学习的人机协同控制方法

By employing a human-machine collaborative control method based on fuzzy rule self-learning, the problem of multi-source risk fusion and dynamic allocation of control rights in autonomous driving systems under complex driving scenarios was solved, realizing collaborative steering control between the driver and the controller, and improving vehicle safety and stability.

CN122166150BActive Publication Date: 2026-07-17CHANGCHUN UNIV OF TECH
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202610638664.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-05-11
Publication Date
2026-07-17
Estimated Expiration
2046-05-11

AI Technical Summary

Technical Problem

Existing autonomous driving systems struggle to achieve multi-source risk fusion identification, online updating of fuzzy rules, dynamic allocation of human-machine control, and game-theoretic collaborative control in complex driving scenarios, resulting in instability and insufficient safety in the human-machine collaborative control process.

Method used

A human-machine collaborative control method based on fuzzy rule self-learning is adopted. By applying reinforcement learning to the risk cognition and fuzzy rule layers, a multi-source driving risk quantification model is constructed. Combined with the expected path module, collision risk identification module, driving state identification module, driving risk fuzzy identification module, reinforcement learning module and non-cooperative game module, collaborative steering control between driver and controller is achieved.

Benefits of technology

It improves the adaptability and accuracy of human-machine collaborative control, coordinates conflicts between human and machine control intentions, and enhances the vehicle's path tracking performance, lateral control stability, and driving safety in complex driving scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122166150B_ABST
    Figure CN122166150B_ABST
Patent Text Reader

Abstract

本发明基于一种模糊规则自学习的人机协同控制方法，旨在解决多源风险信息融合不足及人机控制权与模糊规则的动态调整问题。本发明涉及自动驾驶车辆技术领域。期望路径模块结合车辆状态信息，输出驾驶员与控制器期望路径；驾驶风险预测模块根据驾驶员与控制器期望路径、车辆状态信息以及优化后的模糊规则，输出驾驶员权重、控制器权重和当前模糊规则；强化学习模块根据驾驶总风险、车辆状态信息和当前模糊规则，对模糊规则进行在线优化，输出优化后的模糊规则；非合作博弈模块整合驾驶员权重、控制器权重、驾驶员与控制器期望路径以及车辆状态信息，通过非合作博弈优化出驾驶员与控制器最优转向角，实现人机共驾车辆的协同转向控制。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • A vehicle driving control allocation system in human-machine co-driving

    CN109885040B

  • Automatic driving behavior planning method based on fuzzy control

    CN112068542A

  • Reinforcement learning and game theory integrated dynamic cooperative steering control method

    CN120630727B

  • Fuzzy rule-based man-machine co-driving control right flexible transfer method and system

    CN113650609A

  • Cooperative steering control method considering man-machine mutual reliability

    CN121386428A