Lazy-DaSH: Lazy Approach for Hypergraph-based Multi-robot Task and Motion Planning

2025-04-07

AI Summary

To address scalability bottlenecks—such as state-space explosion and prohibitive planning time—in large-scale multi-robot object rearrangement, this paper proposes a hierarchical lazy-validation framework. The method decouples task and motion planning via a layered architecture with tight coupling through constraint feedback. Its key contributions are: (1) a novel lazy validation mechanism that dynamically identifies and verifies only the motion feasibility of essential subspaces during high-level task planning, eliminating exhaustive precomputation; (2) a constraint feedback mechanism enabling efficient backward propagation of motion constraints to the task layer; and (3) hypergraph-based modeling coupled with constraint propagation to drastically compress the state-space representation. Experiments demonstrate that the approach scales to robot and object counts over twice those supported by DaSH, reduces planning time by an order of magnitude, and exhibits strong scalability and adaptive conflict resolution across four diverse rearrangement scenarios.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We introduce Lazy-DaSH, an improvement over the recent state of the art multi-robot task and motion planning method DaSH, which scales to more than double the number of robots and objects compared to the original method and achieves an order of magnitude faster planning time when applied to a multi-manipulator object rearrangement problem. We achieve this improvement through a hierarchical approach, where a high-level task planning layer identifies planning spaces required for task completion, and motion feasibility is validated lazily only within these spaces. In contrast, DaSH precomputes the motion feasibility of all possible actions, resulting in higher costs for constructing state space representations. Lazy-DaSH maintains efficient query performance by utilizing a constraint feedback mechanism within its hierarchical structure, ensuring that motion feasibility is effectively conveyed to the query process. By maintaining smaller state space representations, our method significantly reduces both representation construction time and query time. We evaluate Lazy-DaSH in four distinct scenarios, demonstrating its scalability to increasing numbers of robots and objects, as well as its adaptability in resolving conflicts through the constraint feedback mechanism.

Problem

• Improving scalability in multi-robot task planning
• Reducing planning time via lazy motion validation
• Enhancing adaptability with constraint feedback mechanism

Innovation

• Hierarchical task and motion planning approach
• Lazy validation of motion feasibility
• Constraint feedback mechanism for efficiency