Beyond Robustness: Learning Unknown Dynamic Load Adaptation for Quadruped Locomotion on Rough Terrain

TL;DR

This paper introduces a novel load characteristics modeling approach combined with reinforcement learning to enable quadruped robots to adapt to unknown dynamic loads on rough terrain, improving stability and performance.

Contribution

The work presents a general load modeling method integrated with RL for load adaptation, enabling robots to infer and stabilize loads without external sensing.

Findings

Outperforms existing methods in load resistance and stabilization

Effective in sim-to-real deployment for real scenarios

Enhances quadruped locomotion under heavy loads on rough terrain

Abstract

Unknown dynamic load carrying is one important practical application for quadruped robots. Such a problem is non-trivial, posing three major challenges in quadruped locomotion control. First, how to model or represent the dynamics of the load in a generic manner. Second, how to make the robot capture the dynamics without any external sensing. Third, how to enable the robot to interact with load handling the mutual effect and stabilizing the load. In this work, we propose a general load modeling approach called load characteristics modeling to capture the dynamics of the load. We integrate this proposed modeling technique and leverage recent advances in Reinforcement Learning (RL) based locomotion control to enable the robot to infer the dynamics of load movement and interact with the load indirectly to stabilize it and realize the sim-to-real deployment to verify its effectiveness in real scenarios. We conduct extensive comparative simulation experiments to validate the effectiveness and superiority of our proposed method. Results show that our method outperforms other methods in sudden load resistance, load stabilizing and locomotion with heavy load on rough terrain. \href{https://leixinjonaschang.github.io/leggedloadadapt.github.io/}{Project Page}.