用人类动作数据引导机器人学习自然协调的全身操作技能
DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
- 用人类动作数据训练扩散模型作为先验，指导强化学习
- 在仿真中成功完成开抽屉、抓取等复杂任务，效果优于纯强化学习
- 生成动作更自然，利于从仿真到真实机器人的迁移
我们提出 DreamControl，一种学习自主全身人形机器人技能的新方法。该方法结合扩散模型与强化学习（RL）的优势：核心创新在于使用基于人类运动数据训练的扩散先验，指导仿真环境中的强化学习策略完成特定任务（如打开抽屉或抓取物体）。实验表明，这种受人类动作启发的先验使强化学习能够发现直接使用强化学习无法达成的解决方案；同时，扩散模型天然生成自然的动作，有助于提升仿真到现实的迁移能力。我们在 Unitree G1 机器人上验证了 DreamControl 在多种挑战性任务上的有效性，这些任务涉及上下肢协同控制与物体交互。
原文摘要 · Abstract (English)
We introduce DreamControl, a novel methodology for learning autonomous whole-body humanoid skills. DreamControl leverages the strengths of diffusion models and Reinforcement Learning (RL): our core innovation is the use of a diffusion prior trained on human motion data, which subsequently guides an RL policy in simulation to complete specific tasks of interest (e.g., opening a drawer or picking up an object). We demonstrate that this human motion-informed prior allows RL to discover solutions unattainable by direct RL, and that diffusion models inherently promote natural looking motions, aiding in sim-to-real transfer. We validate DreamControl's effectiveness on a Unitree G1 robot across a diverse set of challenging tasks involving simultaneous lower and upper body control and object interaction. Project website at https://genrobo.github.io/DreamControl/
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。