A Framework for Flexible Humanoid Robot Control Based on CBR augmented GP

摘要

Humanoid robots are high-dimensional systems; thus it is very difficult for Genetic Programming (GP) to evolve control programs for humanoid robots. In this paper, we propose a framework for GP to generate control programs for humanoid robots. The key idea in our approach is to represent target task with abstract behaviors by Genetic Programming in simplified simulation and get a prototype of the control program then interpret it with Case-Based Reasoning (CBR) in the real world environments. Accordingly, our proposed approach consists of two stages: the evolution stage and the adaptation stage. In the first stage, the prototype of the control program is evolved based on abstract behaviors in a highly simplified simulation. In the second stage, the best control program is applied to a physical robot thereby adapting it to the real world environments by using CBR. Experimental results show that our approach can generate robust control programs that can easily overcome reality gap. We declare that this approach provides a general layered framework for generating control programs for complex systems with GP.