无需配对数据，让机器人学会人类触觉动作。
TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment
- 用修正流模型将人机触觉信号映射到共享隐空间。
- 仅用5分钟人类数据即可完成跨任务迁移，支持零样本转移。
- 适合触觉控制、人机协作等高精度操作场景。
通过可穿戴设备（如触觉手套）收集的人类示范能快速提供灵巧操作的监督信号，且依赖丰富的自然触觉反馈。然而，如何将人类采集的触觉信号迁移到具有不同传感模态和身体结构的机器人上仍是关键挑战。现有方法通常假设触觉传感器相同、需成对数据，且忽略人机间的实体差异，限制了可扩展性和通用性。我们提出TactAlign，一种跨实体触觉对齐方法，可在无配对数据、无手动标签或特权信息的情况下，将人类触觉观测与机器人触觉观测映射至共享隐空间。该方法利用手-物体交互生成伪配对，实现低成本隐空间传输。实验表明，TactAlign在多个接触密集型任务（翻转、插入、开盖）中显著提升人到机器人策略迁移效果；可泛化至未见过的物体与任务，仅需少于5分钟人类数据；并在高度灵巧的任务（拧灯泡）中实现零样本迁移。
原文摘要 · Abstract (English)
Human demonstrations collected by wearable devices (e.g., tactile gloves) provide fast and dexterous supervision for policy learning, and are guided by rich, natural tactile feedback. However, a key challenge is how to transfer human-collected tactile signals to robots despite the differences in sensing modalities and embodiment. Existing human-to-robot (H2R) approaches that incorporate touch often assume identical tactile sensors, require paired data, and involve little to no embodiment gap between human demonstrator and the robots, limiting scalability and generality. We propose TactAlign, a cross-embodiment tactile alignment method that transfers human-collected tactile signals to a robot with different embodiment. TactAlign transforms human and robot tactile observations into a shared latent representation using a rectified flow, without paired datasets, manual labels, or privileged information. Our method enables low-cost latent transport guided by hand-object interaction-derived pseudo-pairs. We demonstrate that TactAlign improves H2R policy transfer across multiple contact-rich tasks (pivoting, insertion, lid closing), generalizes to unseen objects and tasks with human data (less than 5 minutes), and enables zero-shot H2R transfer on a highly dexterous tasks (light bulb screwing).
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。