Chaos-driving Robotic Intelligence for Catching Fish

We tackle a fish-catching task under a visual feedback hand-eye system with catching net. The fishes change escaping trajectory or speed up when being threatened as the net attached at hand approaches to them. Furthermore, as the time of tracking and catching process flows, the fish can somewhat get accustomed to the hand motion pattern and gradually find out new strategies on how to escape from the bothering net. For example, the fish can swim slowly along the pool edge where the net is forbidden to enter or keep a reasonable distance from the net as if it knows the visual servoing system bears steady state error by constant speed escaping. For the sake of such innate ability being widely existed in animal´s behavior, the catching operation becomes tough and some effective intelligent method needs to be conceived to go beyond the fish´s intelligence. The purpose of this research is to construct intelligent system to be able to exceed the fish´s intelligence to survive. Then we embed chaotic motion into the hand motion of robot, and we have shown the chaotic net motion can overcome the fish escaping strategies