通过多尺度对比学习，让机器人自动避开无法通行的路径区域。
Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning
- 用多尺度流形学习将关节配置映射到潜在空间，生成连通性感知表示。
- 实验显示成功率提升1.9倍，规划时间减少至43%。
- 适合需要高效避障与复杂运动规划的机器人任务。
受限运动规划的目标是在满足特定任务约束的前提下连接起始与目标配置。当配置位于互不连通的区域时，即存在本质上相互不可达（EMD）组件，运动规划会变得低效甚至不可行。约束进一步将可行空间限制在低维子流形上，而冗余性则引入额外复杂性——单个末端执行器姿态可能对应无穷多个逆运动学解，这些解可能形成离散的自运动流形。本文通过学习一种连通性感知表示，在规划前筛选起始与目标配置。通过跨局部到全局邻域范围的多尺度流形学习，将关节配置嵌入潜在空间，并利用聚类生成伪标签以监督对比学习框架。所提方法提供连通性感知度量，引导选择位于连通区域内的起始与目标配置，避免进入EMD区域，从而显著提高成功率并缩短规划时间。在多种操作任务上的实验表明，该方法相较基线实现1.9倍的成功率提升，规划时间降低为0.43倍。
原文摘要 · Abstract (English)
The objective of constrained motion planning is to connect start and goal configurations while satisfying task-specific constraints. Motion planning becomes inefficient or infeasible when the configurations lie in disconnected regions, known as essentially mutually disconnected (EMD) components. Constraints further restrict feasible space to a lower-dimensional submanifold, while redundancy introduces additional complexity because a single end-effector pose admits infinitely many inverse kinematic solutions that may form discrete self-motion manifolds. This paper addresses these challenges by learning a connectivity-aware representation for selecting start and goal configurations prior to planning. Joint configurations are embedded into a latent space through multi-scale manifold learning across neighborhood ranges from local to global, and clustering generates pseudo-labels that supervise a contrastive learning framework. The proposed framework provides a connectivity-aware measure that biases the selection of start and goal configurations in connected regions, avoiding EMDs and yielding higher success rates with reduced planning time. Experiments on various manipulation tasks showed that our method achieves 1.9 times higher success rates and reduces the planning time by a factor of 0.43 compared to baselines.
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。