LLM-Grounded Dynamic Task Planning with Hierarchical Temporal Logic for Human-Aware Multi-Robot Collaboration

2026-02-10

AI Summary

This work addresses the challenge that task plans generated by large language models (LLMs) for multi-robot systems often lack kinematic feasibility, while traditional formal methods—such as linear temporal logic (LTL)—struggle to meet real-time demands in dynamic environments and long-horizon tasks. To bridge this gap, the paper proposes a neuro-symbolic framework that uniquely translates high-level semantic understanding from LLMs into hierarchical LTL specifications. By integrating receding-horizon planning with real-time perception, the approach enables dynamic rescheduling of both task allocation and path planning in a unified manner. The method preserves formal correctness while significantly enhancing adaptability in open, uncertain environments and improving human-robot interaction fluency. Real-world experiments demonstrate superior performance over existing baselines in both task success rate and planning efficiency.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

While Large Language Models (LLM) enable non-experts to specify open-world multi-robot tasks, the generated plans often lack kinematic feasibility and are not efficient, especially in long-horizon scenarios. Formal methods like Linear Temporal Logic (LTL) offer correctness and optimal guarantees, but are typically confined to static, offline settings and struggle with computational scalability. To bridge this gap, we propose a neuro-symbolic framework that grounds LLM reasoning into hierarchical LTL specifications and solves the corresponding Simultaneous Task Allocation and Planning (STAP) problem. Unlike static approaches, our system resolves stochastic environmental changes, such as moving users or updated instructions via a receding horizon planning (RHP) loop with real-time perception, which dynamically refines plans through a hierarchical state space. Extensive real-world experiments demonstrate that our approach significantly outperforms baseline methods in success rate and interaction fluency while minimizing planning latency.

Problem

• Large Language Models
• Linear Temporal Logic
• Multi-Robot Collaboration
• Dynamic Task Planning
• Kinematic Feasibility

Innovation

• neuro-symbolic planning
• hierarchical LTL
• receding horizon planning
• LLM grounding
• human-aware multi-robot collaboration