KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909015629365248 |
|---|---|
| author | Shek, Chak Lam Tariq, Faizan M. Bae, Sangjae Isele, David Gupta, Piyush |
| author_facet | Shek, Chak Lam Tariq, Faizan M. Bae, Sangjae Isele, David Gupta, Piyush |
| contents | Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across 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 25.3% over both LLM-only and PDDL-based variants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04129 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning Shek, Chak Lam Tariq, Faizan M. Bae, Sangjae Isele, David Gupta, Piyush Robotics Artificial Intelligence Emerging Technologies Multiagent Systems Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across 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 25.3% over both LLM-only and PDDL-based variants. |
| title | KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning |
| topic | Robotics Artificial Intelligence Emerging Technologies Multiagent Systems |
| url | https://arxiv.org/abs/2602.04129 |