外观
论文arXiv 2610.2031813 天前
TEMPO算法实现机器人策略端侧测试时自适应，Go2实测性能提升80%
针对机器人部署环境漂移难题，提出TEMPO测试时自适应方法。通过熵正则化与基于分数的记忆机制，在无奖励条件下实现端侧自监督策略优化。MuJoCo仿真最高提升80%，Unitree Go2实物验证有效。
宇树 Go2本文由 AI 根据公开内容整理，可能有误，请以原文为准：Efficient Test-Time Adaptation For Robot Policies（arXiv 2610.20318）
核心内容
针对强化学习策略在粗糙地形、负载变化等部署条件下失效且难以重训的问题，研究提出TEMPO测试时自适应（TTA）框架。该方法允许机器人在无外部奖励信号下，利用冻结预训练Critic作为性能代理进行在线自监督更新。在MuJoCo Playground中覆盖Go1、Go2及G1三种机型与四种典型分布偏移场景，单设备设置下策略性能最高提升达80%。
TEMPO核心技术包含两点：一是引入熵正则化项约束Critic预测分布，缓解严重偏移下的过度自信外推；二是设计受优先回放启发的Score-based Memory，对低价值“困难”观测进行重要性采样，将有限算力聚焦于高信息量部署条件。物理验证环节在Unitree Go2上增加小腿配重模拟负载漂移，全板载实时适配结果显示，其实际运动性能显著优于未适配基线，证实了算法在资源受限边缘端的工程可行性。
关键看点
- 熵正则化机制：对Critic预测分布施加熵促进正则项，抑制模型在严重环境偏移下的过度自信外推，稳定在线更新过程
- 分数引导记忆：采用Score-based Memory优先存储低价值困难样本，结合重要性采样将端侧有限算力集中于最具信息量的部署工况
- 仿真性能增益：在MuJoCo中跨Go1/Go2/G1三机型及四类偏移场景测试，单设备TTA设置下策略性能最高提升幅度达80%
- 实物负载验证：在Unitree Go2真机增加小腿配重模拟负载漂移，全板载自适应运行，实测性能显著优于非适配基线策略
工程与产业观察
该工作为具身智能端侧部署提供了轻量化TTA范式。通过冻结Critic与熵正则化组合，解决了无奖励在线适配的稳定性痛点；Score-based Memory机制有效平衡了边缘计算资源与适配效率。对于需在非结构化环境中长期运行且无法频繁回传数据的足式机器人，该技术显著增强了本体对环境漂移的鲁棒性，降低了运维标定成本。
英文摘要 (Abstract)
Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or manual recalibration is often infeasible under on-device latency and memory constraints. We study test-time adaptation (TTA) for robotic control: adapting a pretrained policy online and in a self-supervised manner during execution, without access to rewards. Our starting point is a lightweight baseline that updates only the actor using a frozen pretrained critic as a deployment-time performance surrogate. Building on this, we introduce TEMPO, a test-time entropy-regularized, memory-guided policy optimization method that stabilizes critic-driven updates under severe shift. TEMPO combines (i) an entropy-promoting regularizer on the critic's predictive distribution to mitigate overconfident extrapolation, and (ii) a score-based memory, inspired by prioritized replay, that prioritizes low-value ("hard") observations and applies importance sampling to focus limited computation on the most informative deployment conditions. Across Go1, Go2, and G1 in MuJoCo Playground under four representative shifts and multiple architectures, TEMPO yields consistent gains, reaching up to 80% improvement in a single-device setting. We further validate on a physical Unitree Go2 with an added calf payload, where fully on-device adaptation improves performance over the non-adapted baseline across real-world episodes.
作者：Motasem Alfarra, Pietro Mazzaglia, Markus Peschl, Daniel Dijkman, Christos Louizos
来源
本页事实对应的公开页面，以原文为准。