Research Analyzer
← Back ICRA 2026

GLaMP: A Grounded Language Model-Based Multi-Agent System for Long-Horizon Robotic Task Planning in Industrial Settings

HONGPENG CHEN, David Navarro-Alarcon, PAI ZHENG

PDF

AI summary

Key figure (auto-extracted from paper)
A closed-loop multi-agent framework combining VLM-driven task graphs, symbolic grounding, and reactive behavior trees significantly improves success rates and robustness for long-horizon industrial robotic tasks.
Grounded Language Models Multi-Agent Systems Long-Horizon Planning PDDL Behavior Trees Industrial Robotics

Problem

Long-horizon industrial robotic planning struggles with predicate drift, symbolic-physical misalignment, and poor error recovery in open-loop pipelines. Existing methods lack reliable mechanisms to maintain consistency across complex, multi-step assembly tasks.

Approach

GLaMP uses a vision-language model to extract hierarchical task graphs from manuals, a perception agent to continuously ground real-time observations into PDDL predicates, and an LLM to compile reactive behavior trees with tiered recovery strategies for online error correction.

Key results

  • Achieves 82–92% success rates across five industrial tasks
  • Outperforms baselines by 5–20% in success rate with lower latency
  • Ablation confirms task graphs, reactive trees, and upstream feedback are essential
  • Enables typed failure classification and adaptive parameter regeneration to prevent predicate drift

Why it matters

Provides a reliable, interpretable planning paradigm for industrial automation, enabling language-driven robots to execute complex, long-horizon assembly tasks with minimal human intervention.

Abstract

This paper proposes GLaMP, a grounded language model–based multi-agent system for long-horizon robotic task planning in industrial settings. GLaMP uses a vision- language model (VLM) agent to infer a hierarchical task graph from manuals, grounds multimodal observations into planning domain definition language (PDDL) predicates to maintain symbolic consistency, and employs an large language model (LLM) behavior-tree planner for interpretable plan generation and execution. Typed-symbolic feedback enables failure-aware re-grounding and fallback replanning. Experiments on five industrial tasks show that GLaMP consistently outperforms representative baselines in success rate, planning latency, and execution time.

Index terms

Intelligent and Flexible Manufacturing Task Planning Assembly

Related papers