Monopedal hopping drone learns agile efficient jumps with energy focus

Dynamics-Informed Reinforcement Learning for Agile and Energy-Efficient Locomotion of a Monopedal Hopping Quadcopter

Robotics

Summary

Controlling a robot that hops quickly on one leg while flying is very hard because of its tricky movements and energy use. The authors created a way for the robot to learn good behaviors by rewarding it for using energy wisely and hopping in a natural rhythm. This helps the robot jump high and move forward quickly without wasting much power. Their tests in simulations show the robot can hop smoothly and save a lot of energy compared to usual methods.

What this means in practice

Authors

Ruigang Chen, Qi Zhang, Zhicheng Zhong, Zhuorui Yun, Yizhar Or, Mingyi Liu

Abstract

Although aerial-legged robots offer combined agility and efficiency, controlling high-speed hopping under complex hybrid dynamics is challenging. Reinforcement Learning (RL) is promising but prone to energy-inefficient "reward hacking". We propose a Dynamics-Informed RL framework for a monopedal hopping quadcopter. By embedding a target Specific Energy into the reward, we constrain the optimization to a physically viable energy manifold, ensuring stable hopping behaviour. By rewarding the phase-consistent behavior, it can encourage bio-inspired stance-phase impulse. Furthermore, penalizing the electro-mechanical power waste induces the motors generate an efficient impulse. This enables the policy to inject energy strictly during spring restitution without heuristic state machines. MuJoCo simulations validate robust height regulation and forward velocity tracking up to 2.0 m/s despite severe attitude-contact coupling. Ultimately, our approach yields a highly agile hopping gait, reducing energy consumption by 82% and 73% compared to hovering baselines and inefficiency baseline, respectively.