Personalized Design to Enhance Consumers’ Acceptance of Intelligent Driving Products: A Shared Control Methodology Considering Individual Driver Differences

Intelligentization is an inevitable trend in the development of modern vehicles. However, the diversity and nonprofessional nature of drivers present significant challenges to the design and development of intelligent vehicles. Understanding drivers’ highly individualized behaviors and providing personalized shared control based on these behaviors are critical to enhancing consumers’ acceptance of intelligent driving products. This paper introduces the concept of handling inverse dynamics into the human-machine shared control problem, proposing a personalized human-machine shared control architecture based on the handling inverse process. First, a driver behavior prediction model capable of characterizing driver behavioral differences is established through parameter identification. Combining the driver behavior prediction model, vehicle dynamics model, and road model, a multi-constrained generalized human-machine shared control model is constructed. Subsequently, the human-machine shared control problem is transformed into a multi-constrained optimization problem. And a novel numerical optimization solving method combining an adaptive solving strategy and a node recycling mechanism is proposed. Finally, the effectiveness of the proposed shared control framework is tested and validated on a driver-in-the-loop test platform. The results demonstrate that the proposed framework can provide personalized shared control tailored to individual driver behavior differences.