Trajectory Tracking Control for Mobile Robots Using Reinforcement Learning and PID
- 16 Downloads
In this paper, a novel algorithm of trajectory tracking control for mobile robots using the reinforcement learning and PID is proposed. The Q-learning and PID are adopted for tracking the desired trajectory of the mobile robot. The proposed method can reduce the computational complexity of reward function for Q-learning and improve the tracking accuracy of mobile robot. The effectiveness of the proposed algorithm is demonstrated via simulation tests.
KeywordsTrajectory tracking control Reinforcement learning Q-learning PID
This work was supported by the Fundamental Research Funds for the Central Universities under Grant 2019JBM004.
- Jiang Z, Fan W, Liu W, Zhu B, Jinjing G (2018b) Reinforcement learning approach for coordinated passenger inflow control of urban rail transit in peak hours. Transp Res 88:1–16Google Scholar
- Shah H, Gopal M (2016) Model-free predictive control of nonlinear processes based on reinforcement learning. Int Fed Autom Control 49(1):89–94Google Scholar