发表机构
Center for AI & Robotics; New York University Abu Dhabi（人工智能与机器人中心; 纽约大学阿布扎比分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对冗余机械臂表面覆盖问题，提出基于广义生成树的离线与在线联合生成树覆盖算法，通过多IK解建模为广义最小生成树，实现无重复覆盖路径，仿真验证了其高效性。
AI 中文摘要
使用任务冗余机械臂进行表面覆盖具有挑战性，因为每个表面点可能对应多个逆运动学（IK）解，且配置选择对运动质量影响显著。本文将经典的生成树覆盖（STC）方法扩展到冗余机械臂，通过离线与在线联合生成树覆盖（JSTC）算法实现。离线JSTC为每个网格单元采样多个逆运动学（IK）解，并将问题建模为广义最小生成树（GMST），为每个单元选择一个配置，并追踪生成的树以获得无重复访问的覆盖路径。在线JSTC在动态网格更新下，通过可行性与代价评估逐步扩展和回溯生成树。仿真结果表明，与其他方法相比，离线JSTC减少了计算时间、重新配置次数和关节运动，而在线JSTC在动态场景中实现了快速的逐步规划。
英文摘要
Surface coverage with task-redundant manipulators is challenging because each surface point may admit multiple inverse kinematics (IK) solutions, and configuration choices strongly affect motion quality. This paper extends the classical Spanning Tree Coverage (STC) method to redundant manipulators through offline and online Joint Spanning Tree Coverage (JSTC) algorithms. Offline JSTC samples multiple Inverse Kinematics (IK) solutions per grid cell and formulates the problem as a Generalized Minimum Spanning Tree (GMST), selecting one configuration per cell and tracing the resulting tree to obtain a non-revisiting coverage path. Online JSTC incrementally expands and backtracks a spanning tree with feasibility and cost evaluation while handling dynamic grid updates. Simulation results show that offline JSTC reduces computation time, reconfigurations, and joint motion compared to other methods, while online JSTC achieves fast per-step planning in dynamic scenarios.
CommentsAccepted for publication in IROS 2026
