🤖 AI Summary
This work addresses multi-step natural language (NL) task planning for mobile robots. We formalize NL subtasks as atomic predicates in Linear Temporal Logic (LTL), establishing an LTL-NL task specification framework. To realize this, we propose HERACLEs—a novel hierarchical neuro-symbolic architecture integrating a symbolic planner, a large language model (LLM), and conformal prediction. Conformal prediction serves as an uncertainty-aware interface, enabling users to specify desired success probabilities while guaranteeing LTL constraint satisfaction. We provide theoretical guarantees on controllable task success rates. Experiments demonstrate that HERACLEs significantly outperforms purely LLM-based planners, achieving improvements in task completion rate, LTL consistency, and NL interaction fluency. Our approach bridges the gap between symbolic rigor and neural flexibility in NL-driven robotic planning.
📝 Abstract
This paper addresses planning problems for mobile robots. We consider missions that require accomplishing multiple high-level sub-tasks, expressed in natural language (NL), in a temporal and logical order. To formally define the mission, we treat these sub-tasks as atomic predicates in a Linear Temporal Logic (LTL) formula. We refer to this task specification framework as LTL-NL. Our goal is to design plans, defined as sequences of robot actions, accomplishing LTL-NL tasks. This action planning problem cannot be solved directly by existing LTL planners because of the NL nature of atomic predicates. To address it, we propose HERACLEs, a hierarchical neuro-symbolic planner that relies on a novel integration of (i) existing symbolic planners generating high-level task plans determining the order at which the NL sub-tasks should be accomplished; (ii) pre-trained Large Language Models (LLMs) to design sequences of robot actions based on these task plans; and (iii) conformal prediction acting as a formal interface between (i) and (ii) and managing uncertainties due to LLM imperfections. We show, both theoretically and empirically, that HERACLEs can achieve user-defined mission success rates. Finally, we provide comparative experiments demonstrating that HERACLEs outperforms LLM-based planners that require the mission to be defined solely using NL. Additionally, we present examples demonstrating that our approach enhances user-friendliness compared to conventional symbolic approaches.
