Fuzzy A* quantum multi-stage Q-learning artificial potential field for path planning of mobile robots

Aiming at problem of the efficiency of mobile robots heavily depends on the employed path-planning algorithms that encounter significant challenges from dynamic obstacles and complex environments. This work develops a fuzzy A* quantum multi-stage Q-learning artificial potential field approach, which combines fuzzy A*, quantum multi-stage Q-learning, and artificial potential field (APF) algorithms. The fuzzy A* quantum multi-stage Qlearning APF algorithm combines a fuzzy system with an A* algorithm to improve the A* algorithm. In addition, the fuzzy A* quantum multi-stage Q-learning APF algorithm applies quantum computing methods and multistage training methods to improve the convergence speed of the Q-learning algorithm. If dynamic obstacles exist in environments and dynamic obstacles can block the global path, the obtained A* path points are a dopted as sub-goal points for the APF to plan paths. If mobile robots fall into trap areas, the quantum multi-stage Qlearning is then invoked to plan a path between the local minimum trap and the sub-goal point. Except for escaping the local minimum trap, the proposed fuzzy A* quantum multi-stage Q-learning APF has the advantage of consuming less time. The study tests the fuzzy A* quantum multi-stage Q-learning APF on environments with narrow passages and traps. The results verify that the proposed fuzzy A* quantum multi-stage Q-learning APF can navigate beyond complex environment situations and break free from local minimum traps.