Mutual trust based human-machine shared steering control of intelligent vehicles

The allocation of driving authority is critical to the intelligent human-machine shared steering system of vehicles. Currently, the mutual trust levels between the driver and automatic controller are rarely considered when allocating driving authority. However, a thoughtless mutual trust may reduce cooperation efficiency and even cause decision conflicts, leading to a threat to driving safety. To this end, this paper proposes a human-machine shared steering control (SSC) method for intelligent vehicles that considers mutual trust between humans and machines. Firstly, a human-machine mutual trust (HMMT) model was constructed with consideration of the driver’s and vehicle’s capability. Then, a Takagi-Sugeno fuzzy method considering the HMMT level, the driver’s steering angle, the lateral deviation, and the yaw rate is designed. Finally, driver-in-the-loop experiments under three conditions (high-trust, moderate-trust, and low-trust levels) are carried out. The results indicate that the proposed SSC method can minimize driver workload while ensuring driving safety and stability of intelligent human-machine shared vehicles.