Accurate Power Consumption Estimation Method Makes Walking Robots Energy Efficient and Quiet

Power consumption is a frequently over- looked aspect in robotics, especially in the context of legged robots. Nevertheless, improving the efficiency of walking robots is crucial to overcome the current limitations in runtime. This work proposes a novel method for precisely estimating actuator power consumption based on LSTM neural networks. The performance of this approach is benchmarked against currently employed models and val- idated on real hardware using certified instruments. The proposed method is integrated into the Isaac Gym frame- work and utilized to train a power-efficient policy. Instead of optimizing for handcrafted cost functions, such as the often used torque-square minimization, our approach for the first time trains RL policies that minimize the effective energy consumption. Hardware results demonstrate a re- duction of approximately 25% in the robot’s total power consumption, with a notable 50% decrease observed for the knee actuator. Additionally, the newly developed policy generates significantly smoother and quieter motions.