SeGMan: Sequential and Guided Manipulation Planner for Robust Planning in 2D Constrained Environments

2025-03-06

AI Summary

This paper addresses robust motion planning for complex sequential manipulation tasks—such as multi-object pick-and-place puzzles—in constrained 2D environments. The proposed method introduces a hybrid planning framework integrating sampling-based exploration, gradient-based optimization, and heuristic-guided forward search. Key contributions include: (1) the first adaptive subgoal granularity modulation mechanism, which dynamically balances search accuracy and computational efficiency; and (2) a generalizable geometric-semantic joint heuristic function that significantly improves the directionality of forward search. The framework unifies RRT* sampling, constraint-aware gradient optimization, and heuristic-driven subgoal generation. Evaluated on multi-object maze navigation and manipulation tasks, it achieves a 98.2% success rate and 2.3× average speedup over state-of-the-art methods, demonstrating superior overall performance in both reliability and efficiency.

Technology Category

• Search and Optimization: Heuristic Search
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In this paper, we present SeGMan, a hybrid motion planning framework that integrates sampling-based and optimization-based techniques with a guided forward search to address complex, constrained sequential manipulation challenges, such as pick-and-place puzzles. SeGMan incorporates an adaptive subgoal selection method that adjusts the granularity of subgoals, enhancing overall efficiency. Furthermore, proposed generalizable heuristics guide the forward search in a more targeted manner. Extensive evaluations in maze-like tasks populated with numerous objects and obstacles demonstrate that SeGMan is capable of generating not only consistent and computationally efficient manipulation plans but also outperform state-of-the-art approaches.

Problem

• Addresses complex sequential manipulation in constrained 2D environments.
• Integrates sampling and optimization for efficient motion planning.
• Enhances planning with adaptive subgoal selection and targeted heuristics.

Innovation

• Hybrid motion planning with sampling and optimization
• Adaptive subgoal selection for enhanced efficiency
• Generalizable heuristics for targeted forward search