KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning

2026-02-04

AI Summary

This work addresses the challenge of constructing accurate and consistent symbolic representations in heterogeneous multi-robot systems operating in dynamic environments, where existing approaches often rely on manual modeling or neglect heterogeneity and environmental uncertainty. The authors propose KGLAMP, a novel framework that integrates structured knowledge graphs with large language models (LLMs) to automatically generate and continuously update PDDL problem descriptions. This enables perception of environmental changes and inconsistency-driven replanning. By unifying semantic understanding with symbolic reasoning, KGLAMP achieves at least a 25.5% performance improvement over both pure LLM-based and traditional PDDL methods on the MAT-THOR benchmark, significantly enhancing the system’s robustness and adaptability in long-horizon tasks.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Heterogeneous multi-robot systems are increasingly deployed in long-horizon missions that require coordination among robots with diverse capabilities. However, existing planning approaches struggle to construct accurate symbolic representations and maintain plan consistency in dynamic environments. Classical PDDL planners require manually crafted symbolic models, while LLM-based planners often ignore agent heterogeneity and environmental uncertainty. We introduce KGLAMP, a knowledge-graph-guided LLM planning framework for heterogeneous multi-robot teams. The framework maintains a structured knowledge graph encoding object relations, spatial reachability, and robot capabilities, which guides the LLM in generating accurate PDDL problem specifications. The knowledge graph serves as a persistent, dynamically updated memory that incorporates new observations and triggers replanning upon detecting inconsistencies, enabling symbolic plans to adapt to evolving world states. Experiments on the MAT-THOR benchmark show that KGLAMP improves performance by at least 25.5% over both LLM-only and PDDL-based variants.

Problem

• heterogeneous multi-robot systems
• symbolic representation
• plan consistency
• dynamic environments
• long-horizon missions

Innovation

• Knowledge Graph
• Large Language Model
• Multi-robot Planning
• PDDL
• Replanning