Intelligent Fuzzy Q-Learning Control of Humanoid Robots
In this paper, a design methodology for enhancing the stability of humanoid robots is presented. Fuzzy Q-Learning (FQL) is applied to improve the Zero Moment Point (ZMP) performance by intelligent control of the trunk of a humanoid robot. With the fuzzy evaluation signal and the neural networks of FQL, biped robots are dynamically balanced in situations of uneven terrains. At the mean time, expert knowledge can be embedded to reduce the training time. Simulation studies show that the FQL controller is able to improve the stability as the actual ZMP trajectories become close to the ideal case.
KeywordsHumanoid Robot Biped Robot Zero Moment Point Negative Small Positive Medium
Unable to display preview. Download preview PDF.
- 6.Watkins, C.J.C.H.: Learning from Delayed Rewards.PhD Thesis, Cambridge University (1989)Google Scholar