A learning model of a periodic locomotor pattern by the central pattern generator

Many basic locomotor patterns of living bodies are rhythmic, and oscillator y components of physical systems effectively contribute to the generation o f the movement. The control signals for the basic locomotor patterns are ge nerated by the central pattern generator (CPG), which is composed of collec tive neural oscillators, and the activity of the CPG is tightly synchronize d with the movement of the physical systems. That is, appropriate locomotor patterns are realized by mutual synchronization between the physical syste m and the neural system. In this article a simple learning model is propose d to acquire an appropriate parameter set, the intrinsic frequency of the C PG, and the interaction between the CPG and the physical system, in order t o obtain a desired locomotor pattern. The performance of the proposed learn ing model is confirmed by computer simulations and an adaptive control expe riment of a one-dimensional hopping robot.