DexNDM：通过关节级神经动力学模型弥合灵巧手内旋转的现实差距
DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model
AI总结：
提出DexNDM框架，通过关节级动力学模型弥合仿真到现实的差距，使单一策略在真实世界中泛化旋转复杂形状、高长宽比和小尺寸物体，并支持多样手腕姿态，实现高数据效率和鲁棒性。
摘要：
实现泛化的手内物体旋转仍然是机器人学中的一个重大挑战，这主要源于将策略从仿真迁移到现实世界的困难。灵巧操作中复杂且接触丰富的动力学造成了“现实差距”，使得先前的工作局限于受约束的场景，如简单几何形状、有限的物体尺寸和长宽比、受限的手腕姿态或定制的手部。我们通过一种新颖的框架来解决这一仿真到现实的挑战，该框架使得在仿真中训练的单一策略能够泛化到现实世界中各种物体和条件。我们方法的核心是一个关节级动力学模型，该模型通过有效拟合有限量的真实世界收集数据，并相应调整仿真策略的动作，来学习弥合现实差距。该模型通过跨关节分解动力学、将系统级影响压缩为低维变量，并根据每个关节自身的动态特征学习其演化，从而隐式捕获这些净效应，使其具有高度数据效率和跨不同全手交互分布的泛化能力。我们将其与一种全自动数据收集策略配对，该策略以最少的人工干预收集多样化的真实世界交互数据。我们的完整流程展示了前所未有的泛化性：单一策略成功旋转具有复杂形状（如动物）、高长宽比（高达5.33）和小尺寸的挑战性物体，同时处理多样化的手腕方向和旋转轴。全面的真实世界评估和一个用于复杂任务的遥操作应用验证了我们方法的有效性和鲁棒性。网站：https://meowuu7.github.io/DexNDM/
英文摘要：
Achieving generalized in-hand object rotation remains a significant challenge in robotics, largely due to the difficulty of transferring policies from simulation to the real world. The complex, contact-rich dynamics of dexterous manipulation create a "reality gap" that has limited prior work to constrained scenarios involving simple geometries, limited object sizes and aspect ratios, constrained wrist poses, or customized hands. We address this sim-to-real challenge with a novel framework that enables a single policy, trained in simulation, to generalize to a wide variety of objects and conditions in the real world. The core of our method is a joint-wise dynamics model that learns to bridge the reality gap by effectively fitting limited amount of real-world collected data and then adapting the sim policy's actions accordingly. The model is highly data-efficient and generalizable across different whole-hand interaction distributions by factorizing dynamics across joints, compressing system-wide influences into low-dimensional variables, and learning each joint's evolution from its own dynamic profile, implicitly capturing these net effects. We pair this with a fully autonomous data collection strategy that gathers diverse, real-world interaction data with minimal human intervention. Our complete pipeline demonstrates unprecedented generality: a single policy successfully rotates challenging objects with complex shapes (e.g., animals), high aspect ratios (up to 5.33), and small sizes, all while handling diverse wrist orientations and rotation axes. Comprehensive real-world evaluations and a teleoperation application for complex tasks validate the effectiveness and robustness of our approach. Website: https://meowuu7.github.io/DexNDM/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
