Rapid Embodiment Adaptation for Quadrupedal Locomotion

2026-08-02

AI Summary

This work addresses the challenge of locomotion failure in quadrupedal robots caused by joint constraints or abrupt payload changes. To this end, the authors propose an online embodiment adaptation framework that integrates a general-purpose policy trained with embodiment randomization and a lightweight online module. Leveraging a brief history of recent interactions, the framework rapidly estimates changes in embodiment parameters within half a second and explicitly conditions the policy on these updated estimates. Experiments on both simulation and the real-world Unitree Go2 platform demonstrate that the approach effectively handles extreme disturbances—such as complete leg lockout and sudden 5 kg payload additions—significantly outperforming non-adaptive baselines. This study presents the first method capable of real-time, explicit adaptation to unexpected hardware state changes during operation.

Abstract

Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break when hardware properties shift. We introduce an online embodiment adaptation framework for quadrupedal locomotion that infers embodiment parameters from short interaction histories and conditions control on the inferred hardware state. Our method pairs a generalist policy trained under embodiment randomization with a lightweight adaptation module that identifies physical changes within half a second. We evaluate two representative forms of embodiment variation: joint-range constraints and trunk-mass changes, corresponding to joint-level kinematic degradation and body-level dynamic variation. In simulation, the module accurately estimates these changes and enables closed-loop control that substantially outperforms policies conditioned directly on interaction history. On a real Unitree Go2 robot, our system maintains stable locomotion under severe instances of the evaluated changes, including a fully locked leg and a 5 kg payload, where non-adaptive methods fail. These results demonstrate the practicality of explicit online embodiment identification for rapid adaptation to joint-limit and payload-mass changes, and provide a step toward handling broader forms of uncertain, degraded, or changing robot hardware.

Problem

• embodiment adaptation
• quadrupedal locomotion
• hardware variation
• joint-range constraints
• payload-mass changes

Innovation

• online embodiment adaptation
• quadrupedal locomotion
• embodiment randomization
• hardware-aware control
• rapid adaptation