让机器人学会可迁移的表面操作技能，自动提取专家运动规则。
Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks
- 用可解释的原子动作规则解耦几何规划与执行细节。
- 在L型和窗型物体上成功提取速度与姿态调整规则。
- 适合需要跨场景迁移的工业表面作业任务。
机器人表面交互任务（如喷涂、焊接）需精确几何规划与精准运动执行。当前运动规划能生成有效路径，但缺乏人类操作者的专家运动模式；而示范学习常将执行绑定于特定几何，限制泛化能力。本文提出模块化框架，将几何运动规划与执行级知识解耦。专家行为以可解释的原子运动规则表示，如速度缩放、姿态偏移等，系统性地修正几何规划的参考路径。训练多模态神经网络，联合从运动轨迹数据与CAD几何中推断规则参数。在动态仿真中对L型和窗型物体进行评估，结果表明模型能在两种拓扑结构上成功提取速度与姿态调整规则。
原文摘要 · Abstract (English)
Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While modern motion planners generate valid geometric paths, they often lack the expert motor patterns observed in human operators. Conversely, learning from demonstration often tightly couples task execution to the specific training geometry, limiting transferability. We propose a modular framework that decouples geometric motion planning from execution-level expertise. Expert behavior is represented as a vocabulary of interpretable, atomic motor rules, such as velocity scaling and orientation offsets, that systematically modify a geometrically planned reference path. We train a multimodal neural network to infer rule parameters jointly from kinematic trajectory data and CAD model geometry. We evaluate our approach through dynamic simulation on L-shaped and window-shaped objects, demonstrating on simulated data that the model successfully extracts velocity and orientation rules across both topologies.
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。