arXiv 2602.044122026-02cs.ROcs.LG

通过历史条件强化学习和在线蒸馏实现鲁棒的人形机器人控制：HoRD

HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation

Puyue Wang, Jiawei Hu, Yan Gao, Junyan Wang, Yu Zhang, Gillian Dobbie, Tao Gu, Wafa Johal, Ting Dang, Hong Jia

AI总结：

HoRD通过历史条件强化学习和在线蒸馏，使单个策略能零样本适应未知领域，提升人形机器人在动态变化和外部扰动下的鲁棒性和迁移能力。

摘要：

人形机器人在动态、任务规格或环境设置的微小变化下易出现性能下降。我们提出HoRD，一种针对领域偏移的双阶段学习框架。首先通过历史条件强化学习训练高性能教师策略，该策略通过最近的状态-动作轨迹推断潜在动态上下文，实现在线适应多样化的随机动态。其次通过在线蒸馏将教师的鲁棒控制能力转移到基于变压器的学生策略，该策略在稀疏的根相对3D关节关键点轨迹上运行。通过结合历史条件适应与在线蒸馏，HoRD使单个策略能零样本适应未见领域而无需领域特定再训练。大量实验表明，HoRD在鲁棒性和迁移性上优于强基线，特别是在未见领域和外部扰动下。代码和项目页面可在https://tonywang-0517.github.io/hord/获取。

英文摘要：

Humanoid robots can suffer significant performance drops under small changes in dynamics, task specifications, or environment setup. We propose HoRD, a two-stage learning framework for robust humanoid control under domain shift. First, we train a high-performance teacher policy via history-conditioned reinforcement learning, where the policy infers latent dynamics context from recent state--action trajectories to adapt online to diverse randomized dynamics. Second, we perform online distillation to transfer the teacher's robust control capabilities into a transformer-based student policy that operates on sparse root-relative 3D joint keypoint trajectories. By combining history-conditioned adaptation with online distillation, HoRD enables a single policy to adapt zero-shot to unseen domains without per-domain retraining. Extensive experiments show HoRD outperforms strong baselines in robustness and transfer, especially under unseen domains and external perturbations. Code and project page are available at https://tonywang-0517.github.io/hord/.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

AI总结：

摘要：

英文摘要：

相关论文