Abstract
This article proposes a dynamic safety-margin-aware shared steering control framework via a memory membership fusion gain scheduling scheme to enhance authority allocation and path tracking under dynamic driving conditions. First, an intelligent authority allocation strategy is developed based on the real-time estimation of the vehicle dynamic safety margin. This strategy employs an interval type-2 fuzzy logic system to holistically integrate the external collision risk margin and internal vehicle stability margin, providing a comprehensive assessment of multidimensional risks. Second, a memory-based fuzzy control scheme driven by homogeneous polynomials technique is designed to integrate high-order membership degree information from both past and current time instants. This memory mechanism enables the controller to capture temporal dependencies and dynamic coupling relationships in the human–machine shared steering system, leading to more adaptive and informed gain scheduling. The proposed method is validated via driver-in-the-loop simulations in lane-keeping and successive lane-change scenarios. Results demonstrate the improvements in path tracking accuracy, vehicle stability, and reduction of human–machine conflicts compared to existing approaches.
Funding Information
  • National Natural Science Foundation of China (U25B2056)

This publication has 26 references indexed in Scilit: