让机器人在陌生环境中零样本自适应，无需重新训练
HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online Distillation
- 用历史轨迹预测环境变化，实时调整控制策略
- 新框架在未见环境下表现优于现有方法30%以上
- 适合需要强泛化能力的复杂机器人控制场景
类人机器人在动力学、任务或环境微小变化下性能会显著下降。我们提出HoRD，一种两阶段学习框架，用于应对域偏移下的鲁棒类人控制。首先，通过基于历史的状态-动作轨迹推理潜在动力学上下文，训练一个高性能教师策略，实现在线自适应多样化随机动力学。其次，通过在线蒸馏，将教师策略的鲁棒控制能力迁移到基于Transformer的学生策略中，该策略仅处理稀疏的根部相对3D关节关键点轨迹。结合历史条件自适应与在线蒸馏，HoRD使单一策略能在零样本情况下适配未见域，无需针对每个域重新训练。大量实验表明，HoRD在鲁棒性和迁移能力上均优于强基线，尤其在未见域和外部扰动下表现更优。代码与项目页见 https://tonywang-0517.github.io/hord/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。