Vehicle stability self-adaptive control method under low attached road surface multi-source interference
Through the adaptive control method of multimodal data fusion and dynamic torque distribution, the vehicle stability problem under multi-source interference on low-adhesion roads is solved, high-precision adhesion coefficient estimation and interference source observation are achieved, the stability and response speed of the vehicle on low-adhesion roads are improved, and the lateral control of L4 autonomous driving is supported.
Patent Information
- Application Number
- CN202511164871.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-20
- Publication Date
- 2025-09-16
- Estimated Expiration
- 2045-08-20
AI Technical Summary
On low-adhesion roads, vehicles face stability issues caused by multiple sources of interference (such as crosswinds, sudden changes in road adhesion, and brake hydraulic delays). Existing control systems find it difficult to balance path tracking accuracy and yaw stability, and traditional models and perception methods have errors and insufficient redundancy design.
Multimodal environmental data fusion and spatiotemporal convolutional network are used to predict road adhesion coefficient, dynamically correct tire stiffness, and estimate disturbance sources using an enhanced extended state observer. Lyapunov stability theory is combined to allocate control priorities, and torque distribution is optimized through a quadratic programming algorithm to achieve dynamic torque collaborative control.
It achieves high-precision adhesion coefficient estimation and interference source observation, improves the vehicle's stability and response speed on low-adhesion roads, reduces the risk of sideslip and control errors, and supports the lateral control requirements of L4 autonomous driving.