LLM-Grounded Dynamic Task Planning with Hierarchical Temporal Logic for Human-Aware Multi-Robot Collaboration
This work addresses the challenge of enabling non-experts to specify and execute efficient, correct multi-robot tasks in dynamic environments, representing an incremental advance by combining existing LLM and formal method techniques.
The paper tackles the problem of generating kinematically feasible and efficient multi-robot plans from open-world specifications using LLMs, by grounding LLM reasoning into hierarchical LTL specifications and solving a dynamic STAP problem with receding horizon planning, resulting in significant improvements in success rate and interaction fluency while minimizing planning latency in real-world experiments.
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.