用人类操作经验指导机械手旋转，提升跨机型成功率。
DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation
- 将人类示范转为接触条件下的操作能力演化模型
- 在多个机械手上实现57.5%平均成功率，优于基线
- 适合需要精细旋转技能的多类型机器人应用
灵巧物体旋转是一个序列接触问题：每次支撑、释放和重新接触的决策既要实现期望的物体运动，又要为后续旋转步骤准备合适的机械手构型。现有强化学习方法通过在特定机器人手上试错发现运动模式，但未显式考虑每个接触过渡如何影响手部持续旋转的能力。我们提出DexMani框架，将人类示范转化为接触条件下的可操作性演化先验。该先验捕捉了成功的人类接触过渡如何重塑手部可实现的物体旋转方向。DexMani随后学习这一可操作性演化，并用于引导下游强化学习，在具有不同运动学和主动接触配置的机器人上实现旋转技能的迁移。在Shadow Hand、Allegro Hand和XHand上，DexMani在所有评估设置中（包括已见与未见物体）均达到最高成功率。在LEAP Hand上平均成功率达57.5%，显著优于其他基线，且运动更平滑。
原文摘要 · Abstract (English)
Dexterous object rotation is a sequential contact problem: each support, release, and re-contact decision must both produce the desired object motion, and prepare the hand configuration for continued rotation. Existing reinforcement learning methods discover such movement patterns through trial and error on specific robotic hand embodiments, without explicitly accounting for how each contact transition affects the hand's ability to sustain object rotation in subsequent steps. We introduce DexMani, a framework that transfers human demonstrations as contact-conditioned manipulability evolution. This prior captures how successful human contact transitions reshape the object-rotation directions available to the hand. DexMani then learns this manipulability evolution and uses it to guide downstream reinforcement learning, enabling rotation skills to be acquired across robot embodiments with distinct kinematics and active-contact configurations. Across the Shadow Hand, Allegro Hand, and XHand, DexMani achieves the highest success rates in every evaluated setting for both seen and unseen objects. DexMani reaches an average success rate of 57.5% on LEAP Hand, outperforming other baselines and producing smoother rotatory motions. Project site: https://dexmani.github.io
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。