一个模型搞定不同机器人动作迁移，还能零样本泛化。
AdaMorph: Unified Motion Retargeting via Embodiment-Aware Adaptive Transformers
- 用隐式意图空间+自适应提示，统一处理不同机器人形态
- 在12种人形机器人上实现零样本迁移，保持原动作动态特征
- 自适应归一化动态调参，保证动作物理合理性
将人类动作迁移到异构机器人是机器人学中的基础挑战，主要源于不同机器人形态间严重的运动学与动力学差异。现有方法通常需为每种机器人训练专属模型，扩展性差且难以共享运动语义。为此，我们提出AdaMorph，一种统一的神经动作迁移框架，使单个模型可适配多种机器人形态。该方法将人类动作映射到形态无关的隐式意图空间，并通过双重用途的提示机制进行条件生成。不同于简单拼接输入，我们采用自适应层归一化（AdaLN）动态调节解码器特征空间以适应形态约束。此外，通过基于课程的学习目标强制物理合理性，确保姿态与轨迹一致性。在12种不同人形机器人上的实验表明，AdaMorph能有效统一控制异构拓扑，对未见复杂动作表现出强大的零样本泛化能力，同时保留源行为的动态本质。
原文摘要 · Abstract (English)
Retargeting human motion to heterogeneous robots is a fundamental challenge in robotics, primarily due to the severe kinematic and dynamic discrepancies between varying embodiments. Existing solutions typically resort to training embodiment-specific models, which scales poorly and fails to exploit shared motion semantics. To address this, we present AdaMorph, a unified neural retargeting framework that enables a single model to adapt human motion to diverse robot morphologies. Our approach treats retargeting as a conditional generation task. We map human motion into a morphology-agnostic latent intent space and utilize a dual-purpose prompting mechanism to condition the generation. Instead of simple input concatenation, we leverage Adaptive Layer Normalization (AdaLN) to dynamically modulate the decoder's feature space based on embodiment constraints. Furthermore, we enforce physical plausibility through a curriculum-based training objective that ensures orientation and trajectory consistency via integration. Experimental results on 12 distinct humanoid robots demonstrate that AdaMorph effectively unifies control across heterogeneous topologies, exhibiting strong zero-shot generalization to unseen complex motions while preserving the dynamic essence of the source behaviors.
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。