基于强化学习的仿生机器鱼节能研究

利用仿生机器鱼平台, 模拟鱼类集群游动过程, 通过实验方法探究机器鱼集群游动时的能量节省问题。具体地, 将两条机器鱼按照一定的前后距离和左右距离固定在低湍流水洞中, 并正对来流方向; 控制前方(领航)机器鱼游动姿态的变化, 使得后方(跟随)机器鱼处在变化的流场环境中。基于强化学习理论, 建立跟随机器鱼在该流场环境下游动所消耗的能量值与其游动姿态之间的映射关系; 利用该映射关系, 获得跟随机器鱼能量消耗最小值对应的游动姿态信息, 并将该信息反馈至机器鱼运动控制器中, 调整机器鱼游动姿态,达到节省机器鱼能量的目标。

Studies on Energy Saving of Robot Fish Based on Reinforcement Learning

The authors studied energy saving in fish school utilizing a bio-inspired robotic fish platform.Specifically, two robotic fish were fixed in the flow tank against the current with constant left-right distance andfront-back distance; the body posture of the front robotic fish was controlled to generate dynamic fluidenvironments, which would affect the rear robotic fish. Based on reinforcement learning, a relationship wasestablished between energy cost and the body posture of the robotic fish. According to this relationship, the bodyposture could be acquired which resulted in minimum energy cost for the rear robot. This information was furthertransferred to the locomotion controller of the robot to adjust its body posture to save most energy.