无需人类示范，自动发现复杂人形机器人长时程操作动作
MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
- 用大语言模型引导进化搜索，高效探索接触交互序列
- 在多个挑战性任务中成功发现全身协调运动轨迹
- 可部署到真实人形机器人，适用于自主技能生成场景
我们提出 MotionDisco，一种从零开始发现高接触密度、长时程人形机器人运动操作动作的框架，不依赖遥操作或人类示范的动作重定向。该任务极具挑战性，因可能的接触交互组合随任务时长和场景物体数量呈组合爆炸式增长。MotionDisco 通过将大语言模型（LLM）引导的进化搜索与高效的序列式运动学动力学轨迹优化及剪枝策略结合，实现快速发现新技能。大量消融实验表明，该方法能在多个复杂长时程任务中发现成功的全身运动轨迹。最终，通过在发现的轨迹上训练强化学习跟踪策略，将动作成功迁移到真实人形机器人上。这是首个完全通过自动化进化搜索实现并部署长时程人形机器人操作技能的研究。补充视频见：https://youtu.be/DHiVz34QYlw。
原文摘要 · Abstract (English)
We present MotionDisco, a framework that discovers contact-rich, long-horizon humanoid loco-manipulation motions from scratch, without relying on teleoperation or motion retargeting from human demonstrations. This is challenging because the space of possible contact interactions grows combinatorially with the task horizon and the number of objects in the scene. MotionDisco enables rapid discovery of novel motions by coupling a large language model (LLM) guided evolutionary search over sequences of interactions with an efficient sequential kinodynamic trajectory optimizer and pruning strategy, enabling the rapid discovery of novel skills. Through extensive ablation studies, we show that our LLM-guided search discovers successful whole-body trajectories across several challenging long-horizon tasks. Finally, by training reinforcement learning tracking policies on the discovered trajectories, we transfer the motions to a real humanoid robot. This is the first work to discover and deploy long-horizon humanoid loco-manipulation skills entirely through automated evolutionary search. Supplementary videos of the experiments are available at: https://youtu.be/DHiVz34QYlw.
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。