Path planning of flocking task for multiple mobile robots based on game theory

To provide a theoretical reference for the development of advanced vehicle control systems and intelligent vehicles, the principal component analysis was used to determine the influence coefficient of multi-information on driving behavior decision-making, and the fuzzy integral fusion algorithm was applied to obtain the running pattern of a vehicle after the task concentration of the driver.

The characteristic of the multi-information stimulation,the task concentration of the driver,and the cooperative reaction behavior are not considered synthetically in the traditional microscopic traffic simulation model,especially for the car-following model which is used to portray the driving behavior.

To reduce the learning status space of complex foraging task and improve the learning speed,a double-deck hierarchical reinforcement learning with share zone is presented.