Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning

2026-03-26

AI Summary

This work addresses the challenge in constrained motion planning where start and goal configurations lying in disconnected regions of the configuration space—often referred to as Exclusion Manifold Disconnectedness (EMD)—lead to planning failure or inefficiency. To overcome this, the authors propose a novel framework that integrates multi-scale manifold embedding with contrastive learning. By clustering high-dimensional redundant configurations to generate pseudo-labels, the method explicitly models the underlying connectivity structure and pre-filters start-goal pairs belonging to the same connected component prior to planning. The approach innovatively incorporates multi-scale neighborhood embeddings and connectivity-aware representations, yielding substantial performance gains: across multiple manipulation tasks, it achieves a 1.9× higher success rate and reduces planning time to 43% of the baseline.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Multiagent Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• constrained motion planning
• essentially mutually disconnected components
• connectivity-aware representation
• kinematic redundancy
• feasible configuration selection

Innovation

• connectivity-aware representation
• multi-scale contrastive learning
• constrained motion planning
• manifold learning
• essentially mutually disconnected components