Learning to Exploit Passive Dynamics for Energy-Efficient Target Hopping of a Spring-Legged Quadcopter

2026-09-14

AI Summary

本文提出了一种直接状态到电机的PPO策略，通过能量流形塑形和效率塑形方法优化单腿四旋翼无人机的跳跃能效，减少了30.7%电能消耗。

Abstract

Combining aerial thrust with spring-loaded hopping makes monopedal quadcopters promising for locomotion over complex terrain, but heuristic proportional-integral-derivative (PID) tuning limits coordination between active thrust and passive contact dynamics. We present a direct estimated-state-to-motor Proximal Policy Optimization (PPO) policy that commands four motors without an explicit hopping state machine or low-level attitude PID. Its reward combines Energy-Manifold Shaping for mass-normalized vertical-energy tracking and apex-state anchoring with Efficiency Shaping, which uses a history-aware power estimator to penalize general power use, impose an additional airborne-power cost, and penalize airborne near-stationarity. In representative hardware runs, the PPO-based control stack reduced cycle-averaged measured electrical power by 30.7% and mean total normalized thrust by 49.8% relative to the tuned PID-based control stack, while retaining repeatable commanded-height hopping and more concentrated landings. These observations are consistent with improved use of passive dynamics and reduced measured electrical demand.

Problem

• Energy-Efficient
• Target Hopping
• Spring-Legged Quadcopter
• Passive Dynamics
• Complex Terrain

Innovation

• Proximal Policy Optimization
• Energy-Manifold Shaping
• Efficiency Shaping
• Passive Dynamics