Dynamic balance of a biped robot using fuzzy reinforcement learning agents

✍ Scribed by Changjiu Zhou; Qingchun Meng

• Publisher: Elsevier Science
• Year: 2003
• Tongue: English
• Weight: 412 KB
• Volume: 134
• Category: Article
• ISSN: 0165-0114
• DOI: 10.1016/s0165-0114(02)00236-1

✦ Synopsis

This paper presents a general fuzzy reinforcement learning (FRL) method for biped dynamic balance control. Based on a neuro-fuzzy network architecture, di erent kinds of expert knowledge and measurement-based information can be incorporated into the FRL agent to initialise its action network, critic network and=or evaluation feedback module so as to accelerate its learning. The proposed FRL agent is constructed and veriÿed using the simulation model of a physical biped robot. The simulation analysis shows that by incorporation of the human intuitive balancing knowledge and walking evaluation knowledge, the FRL agent's learning rate for side-to-side and front-to-back balance of the simulated biped can be improved. We also demonstrate that it is possible for a biped robot to start its walking with a priori knowledge and then learn to improve its behaviour with the FRL agents.