ManipTrans：通过残差学习实现高效灵巧双臂操作迁移
ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning
浏览论文内容
中文总结 AI 辅助
ManipTrans通过两阶段残差学习，高效将人类双臂技能迁移至仿真灵巧机器人手，创建含3.3K片段的DexManipNet数据集，在成功率、保真度和效率上超越现有方法。
中文摘要 AI 辅助
人类双手在交互中扮演核心角色，推动了灵巧机器人操作研究的增长。数据驱动的具身AI算法需要精确、大规模、类人的操作序列，而通过传统强化学习或真实世界遥操作难以获得这些数据。为解决这一问题，我们提出ManipTrans，一种新颖的两阶段方法，用于在仿真中高效地将人类双手技能迁移到灵巧机器人手上。ManipTrans首先预训练一个通用轨迹模仿器来模仿手部运动，然后在交互约束下微调特定残差模块，从而实现复杂双臂任务的高效学习和精确执行。实验表明，ManipTrans在成功率、保真度和效率方面均超越现有最先进方法。利用ManipTrans，我们将多个手-物体数据集迁移到机器人手上，创建了DexManipNet，这是一个大规模数据集，包含笔帽盖合和瓶盖拧开等此前未探索的任务。DexManipNet包含3.3K条机器人操作片段，且易于扩展，有助于进一步训练灵巧手的策略，并支持真实世界部署。
英文摘要
Human hands play a central role in interacting, motivating increasing research in dexterous robotic manipulation. Data-driven embodied AI algorithms demand precise, large-scale, human-like manipulation sequences, which are challenging to obtain with conventional reinforcement learning or real-world teleoperation. To address this, we introduce ManipTrans, a novel two-stage method for efficiently transferring human bimanual skills to dexterous robotic hands in simulation. ManipTrans first pre-trains a generalist trajectory imitator to mimic hand motion, then fine-tunes a specific residual module under interaction constraints, enabling efficient learning and accurate execution of complex bimanual tasks. Experiments show that ManipTrans surpasses state-of-the-art methods in success rate, fidelity, and efficiency. Leveraging ManipTrans, we transfer multiple hand-object datasets to robotic hands, creating DexManipNet, a large-scale dataset featuring previously unexplored tasks like pen capping and bottle unscrewing. DexManipNet comprises 3.3K episodes of robotic manipulation and is easily extensible, facilitating further policy training for dexterous hands and enabling real-world deployments.
发表机构
- State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）
- Tsinghua University（清华大学）
- Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。
