Reinforcement learning path planning method introducing artificial potential field

Abstract

The invention discloses a reinforcement learning path planning method for introducing an artificial potential field, and the method comprises the following steps: S1, building a grid map, introducinga gravitational field function to initialize a state value, and obtaining a simulation environment for training a reinforcement learning intelligent agent; S2, initializing algorithm parameters; S3, selecting an action by adopting a dynamic factor adjustment strategy; S4, executing an action, and updating a Q value; S5, repeatedly executing the step 3 and the step 4 until a certain step number ora certain convergence condition is reached; S6, selecting the action with the maximum Q value in each step, and obtaining the optimal path; S7, sending the optimal path to a controller of the mobile robot, and controlling the mobile robot to walk according to the optimal path. Compared with a traditional algorithm, the improved Q-learning algorithm has the advantages that the path planning time isshortened by 85.1%, the number of iterations before convergence is reduced by 74.7%, and meanwhile, the convergence result stability of the algorithm is also improved.

Description

technical field [0001] The invention relates to the technical field of robot path planning, in particular to a reinforcement learning path planning method that introduces an artificial potential field. Background technique [0002] With the development of science and technology, more and more mobile robots have entered people's daily life. The problem of path planning for mobile robots has also received more and more attention. Path planning technology can help the robot avoid obstacles and plan an optimal movement route from the starting point to the target point under the condition of referring to a certain index. According to the known degree of environmental knowledge in the path planning process, path planning can be divided into global path planning and local path planning. Among them, the widely used global path planning algorithms include A* algorithm, dijkstra algorithm, visual graph method, free space method, etc.; the local path planning algorithms include artif...

AI Technical Summary

Problems solved by technology

The traditional Q-learning algorithm has the following problems: (1) During the initialization process, all Q values ​​are set to 0 or random values, which makes the agent only search blindly at the initial stage, resulting in There are too many invalid iterations in the stage; (2) ε-greedy strategy is adopted in the action selection, too large ε value will make the agent explore more environments and it is not easy to converge, and too small ε value will cause the agent to be sensitive to the environment. Finding a suboptimal solution due to insufficient exploration, it is difficult to balance the relationship between exploration and utilization

Images