An adaptive gain parameters algorithm for path planning based on reinforcement learning

In this paper, the problem of adaptive variable gain parameters for path planning is studied for the case for a mobile robot moving in an environment filled with obstacles which shapes and positions are known. An adaptive variable gain parameters algorithm based on reinforcement learning was proposed. It is obtained by using linear reinforcement and predictive control method. The presented algorithm accomplished adaptive variable gain parameters online, and the convergence speed of the path planning is increased about ten times. Simulation examples show that the presented algorithm is effective. Moreover, the method presented can also be applied to the adaptive variable parameter issue in other scientific iteration algorithms.