A GIM-Based Biomimetic Learning Approach for Motion Generation of a Multi-Joint Robotic Fish

In this paper, we propose a biomimetic learning approach for motion generation of a multi-joint robotic fish. Based on a multi-joint robotic fish model, two basic Carangiform swimming patterns, namely "cruise" and "C sharp turning", are extracted as training samples from the observations of real fish swimming. A General Internal Model (GIM), which is an imitation of Central Pattern Generator (CPG) in nerve systems, is adopted to learn and to regenerate coordinated fish behaviors. By virtue of the universal function approximation ability and the temporal/spatial scalabilities of GIM, the proposed learning approach is able to generate the same or similar fish swimming patterns by tuning two parameters. The learned swimming patterns are implemented on a multi-joint robotic fish in experiments. The experiment results verify the effectiveness of the biomimetic learning approach in generating and modifying locomotion patterns for the robotic fish.