Abstract | ||
---|---|---|
This paper proposes a novel self-learning PD (Proportional-Derivative) control method for mobile robot path-tracking problems. In the self-learning PD control method, a reinforcement-learning (RL) module is used to automatically fine-tune the PD coefficients with only evaluative feedback. The optimization of the PD coefficients is modeled as a Markov decision problem (MDP) with continuous state space. Using an improved AHC (Adaptive Heuristic Critic) learning control method based on recursive least-squares algorithms, the near-optimal control policies of the MDP are approximated efficiently. Besides its simplicity, the self-learning PD controller can be adaptive to uncertainties in the environment as well as the mobile robot dynamics. Simulation and experimental results on a real mobile robot illustrate the effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-28648-6_5 | ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 2 |
Keywords | Field | DocType |
mobile robot,dynamic simulation,optimal control,reinforcement learning,state space | Heuristic,PID controller,Control theory,Computer science,Artificial intelligence,Markov decision problem,State space,Machine learning,Path tracking,Mobile robot,Recursion,Reinforcement learning | Conference |
Volume | ISSN | Citations |
3174 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xin Xu | 1 | 1365 | 100.22 |
Xuening Wang | 2 | 21 | 2.04 |
Dewen Hu | 3 | 1290 | 101.20 |