仅用一次样本就能让机器人学会新动作，还保持平衡不撞腿。
One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors
- 用一个非行走动作+辅助行走数据，配合预训练模型快速生成新动作
- 在CMU数据集上优于基线，动作自然且无碰撞
- 适合想快速适配新动作的机器人研发者
全身类人机器人运动是机器人学中的核心挑战，需兼顾平衡、协调与适应性以实现类人行为。然而现有方法通常需要每种动作多个训练样本，导致高质量人体动作数据集收集耗时费力。为此，我们提出一种数据高效适配方法：仅需一个非行走目标样本，结合辅助行走动作和已训练的行走基础模型，即可学习新动作。核心思路是利用保序最优传输计算行走与非行走序列间的距离，并沿测地线插值生成中间姿态骨架，再优化为无碰撞配置，最终重定向至类人机器人并融入模拟环境，通过强化学习完成策略适配。在CMU MoCap数据集上的实验表明，本方法在各项指标上持续优于基线。代码已开源：https://github.com/hhuang-code/One-shot-WBM。
原文摘要 · Abstract (English)
Whole-body humanoid motion represents a fundamental challenge in robotics, requiring balance, coordination, and adaptability to enable human-like behaviors. However, existing methods typically require multiple training samples per motion, rendering the collection of high-quality human motion datasets both labor-intensive and costly. To address this, we propose a data-efficient adaptation approach that learns a new humanoid motion from a single non-walking target sample together with auxiliary walking motions and a walking-trained base model. The core idea lies in leveraging order-preserving optimal transport to compute distances between walking and non-walking sequences, followed by interpolation along geodesics to generate new intermediate pose skeletons, which are then optimized for collision-free configurations and retargeted to the humanoid before integration into a simulated environment for policy adaptation via reinforcement learning. Experimental evaluations on the CMU MoCap dataset demonstrate that our method consistently outperforms baselines, achieving superior performance across metrics. Our code is available at: https://github.com/hhuang-code/One-shot-WBM.
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。