Human-oriented adaptive shared steering control for intelligent vehicles

Abstract

Before autonomous driving is fully realized, human-machine shared control plays a key role in advancing vehicle intelligence. In order to adapt to drivers’ driving abilities as well as to mitigate human-machine conflicts, a novel human-oriented online driving authority optimization method of shared steering is proposed, where a fuzzy control method is used to optimize the driving authority. This method can reduce the driver’s workload and mental load when the drivers and automated driving agent have similar driving intentions. On the other hand, when the automation intention is inconsistent with the human drivers, the human drivers have absolute control over the intelligent vehicle within the vehicle safety zone. To demonstrate the effectiveness of the proposed method, the driving simulator experiments are conducted under four working conditions, namely, manual driving (Manual), low-weighted shared control (SSC-Low), high-weighted shared control (SSC-High), and adaptive fuzzy shared control (SSC-Adaptive), respectively. The experimental results show that compared to SSC-High, SSC-Low, and Manual methods, the proposed SSC-Adaptive method can ensure the vehicle in the safe area while reducing the driver’s workload and mental load.