Gait Parameter Optimization of Quadruped Robot Under Energy Consumption Index Based on Reinforcement Learning

摘要

In this paper, the gait optimization of quadruped bionic robot is studied under the unified energy consumption index. Firstly, an energy consumption index of quadruped robot is established. Secondly, the reinforcement learning method is used to optimize the gait parameters of the quadruped robot, so that the quadruped robot can gradually find the gait parameter combination with the lowest energy consumption in the current state in the interaction with the environment. In order to verify the effectiveness of this method, this paper completes the optimization of gait parameters combined with MIT cheetah software and DDQN network.