LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning

2024/10/28 by Kazuma Obata, Obata, Kazuma, Tatsuya Aoki +7 · 9 citations
Computer Science · #AI-based Problem Solving and Planning #Advanced Software Engineering Methodologies #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2410.21040

openalex publication_date 2024/10/28 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28

Abstract

This study proposes LiP-LLM: integrating linear programming and dependency graph with large language models (LLMs) for multi-robot task planning. In order for multiple robots to perform tasks more efficiently, it is necessary to manage the precedence dependencies between tasks. Although multi-robot decentralized and centralized task planners using LLMs have been proposed, none of these studies focus on precedence dependencies from the perspective of task efficiency or leverage traditional optimization methods. It addresses key challenges in managing dependencies between skills and optimizing task allocation. LiP-LLM consists of three steps: skill list generation and dependency graph generation by LLMs, and task allocation using linear programming. The LLMs are utilized to generate a comprehensive list of skills and to construct a dependency graph that maps the relationships and sequential constraints among these skills. To ensure the feasibility and efficiency of skill execution, the skill list is generated by calculated likelihood, and linear programming is used to optimally allocate tasks to each robot. Experimental evaluations in simulated environments demonstrate that this method outperforms existing task planners, achieving higher success rates and efficiency in executing complex, multi-robot tasks. The results indicate the potential of combining LLMs with optimization techniques to enhance the capabilities of multi-robot systems in executing coordinated tasks accurately and efficiently. In an environment with two robots, a maximum success rate difference of 0.82 is observed in the language instruction group with a change in the object name.

Cited by

• Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration
• GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
• PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language
• RobotFleet: An Open-Source Framework for Centralized Multi-Robot Task Planning
• ELHPlan: Efficient Long-Horizon Task Planning for Multi-Agent Collaboration
• Multi-Robot Task Planning for Multi-Object Retrieval Tasks with Distributed On-Site Knowledge via Large Language Models
• Language-Guided Long Horizon Manipulation with LLM-based Planning and Visual Perception
• DEXTER-LLM: Dynamic and Explainable Coordination of Multi-Robot Systems in Unknown Environments via Large Language Models
• PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation

Related

• SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models
• PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language
• Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures
• LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning
• DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models