Generating chaos with neural-network-differential-equation for intelligent fish-catching robot

We have been investigating a method to compose some intelligent robot. Continuous catching and releasing experiment of several fishes induces the fishes to find some escaping strategies such as staying stationarily at corners of the pool. To make fish-catching robot intelligent more than fish´s adapting and escaping abilities, we have proposed a chaos-generator comprising Neural-Network-Differential-Equation(NNDE) and an evolving mechanism to have the system generate chaotic trajectories as many as possible. We believe that the fish could not be adaptive enough to escape from chasing net with chaos motions since unpredictable chaotic motions of net may go beyond the fish´s adapting abilities to the net motions. In this report we confirmed that the proposed system can generate plural chaos by examining chaotic characters of chaos trajectories generated by NNDE through Lyapunov number, Poincare return map, initial value sensitivity, fractal dimension and bifurcation map.