FARE: Fast-Slow Agentic Robotic Exploration

TL;DR

FARE introduces a hierarchical exploration framework combining large language models for global reasoning with reinforcement learning for local control, significantly improving autonomous robot exploration efficiency.

Contribution

The paper presents FARE, a novel hierarchical exploration method integrating semantic reasoning with local control, employing a modular pruning mechanism for efficiency.

Findings

FARE outperforms state-of-the-art baselines in simulated environments.

FARE successfully deployed on hardware in large-scale building environments.

The architecture effectively decouples semantic reasoning from geometric decision-making.

Abstract

This work advances autonomous robot exploration by integrating agent-level semantic reasoning with fast local control. We introduce FARE, a hierarchical autonomous exploration framework that integrates a large language model (LLM) for global reasoning with a reinforcement learning (RL) policy for local decision making. FARE follows a fast-slow thinking paradigm. The slow-thinking LLM module interprets a concise textual description of the unknown environment and synthesizes an agent-level exploration strategy, which is then grounded into a sequence of global waypoints through a topological graph. To further improve reasoning efficiency, this module employs a modularity-based pruning mechanism that reduces redundant graph structures. The fast-thinking RL module executes exploration by reacting to local observations while being guided by the LLM-generated global waypoints. The RL policy is additionally shaped by a reward term that encourages adherence to the global waypoints, enabling coherent and robust closed-loop behavior. This architecture decouples semantic reasoning from geometric decision, allowing each module to operate in its appropriate temporal and spatial scale. In challenging simulated environments, our results show that FARE achieves substantial improvements in exploration efficiency over state-of-the-art baselines. We further deploy FARE on hardware and validate it in complex, large scale $200m\times130m$ building environment.