发表机构
Autonomous Systems Lab, Technische Universität Wien (TU Wien); Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（自主系统实验室，维也纳工业大学（TU Wien）; 机器人与机电一体化研究所，德国航空航天中心（DLR））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对受限操作任务，提出统一一次性框架，从单个未完成演示学习正反向技能。将演示分阶段，用DMP编码非接触运动，螺旋运动原语表示接触运动，经实验验证，相比基线提升了成功率与鲁棒性。
AI 中文摘要
从演示中学习（LfD）能让机器人直接从专家演示中学习操作技能，但对于涉及几何约束和力交互的接触丰富型任务仍具有挑战性。现有方法通常需要多个完整演示且不支持反向技能执行。本文提出了一个统一的一次性框架，用于受限操作，可从单个可能未完成的演示中学习正向和反向执行。该方法将演示分解为非接触和接触阶段，非接触运动用动态运动原语（DMP）编码，接触运动用通过提出的几何驱动扭转方向分割算法分割的螺旋运动原语序列表示。实验表明，该方法在插销、电池插入、开锁和拧螺丝任务上比分割和一次性轨迹学习基线有更高成功率和鲁棒性。
英文摘要
Learning from demonstration (LfD) enables robots to learn manipulation skills directly from expert demonstrations but remains challenging for contact-rich tasks involving geometric constraints and force interaction. Existing approaches typically require multiple complete demonstrations and do not support reverse skill execution. In this paper, we present a unified one-shot framework for constrained manipulation that learns both forward and reverse execution from a single, possibly unfinished demonstration. Our method decomposes demonstrations into non-contact and contact phases, with non-contact motion encoded with dynamic movement primitives (DMP), and contact motion represented as a sequence of screw motion primitives segmented by our proposed geometry-driven twist-direction segmentation algorithm. During execution, screw primitives are executed sequentially under admittance-guided pose correction and speed regulation, enabling task completion beyond the demonstrated trajectory length as well as reverse skill execution without additional learning data. Experiments on peg insertion, battery insertion, lock opening, and screw driving tasks demonstrate improved success rates and robustness over segmentation and one-shot trajectory learning baselines. Details are available on the project website: https://tuwien-asl.github.io/LfD-Screw/.
