FARE: Fast-Slow Agentic Robotic Exploration

2026-01-21

AI Summary

This work addresses the challenge of coordinating semantic reasoning and local control for autonomous robots operating in unknown environments by proposing a hierarchical exploration framework inspired by the “fast-and-slow thinking” paradigm. The approach leverages a large language model (LLM) to generate high-level semantic strategies while employing reinforcement learning (RL) for low-level navigation, with a modular topological graph pruning mechanism that decouples semantic and geometric decision-making across spatiotemporal scales. Notably, this is the first method to integrate LLMs and RL within a fast-and-slow architecture, incorporating global waypoint guidance and reward shaping. The framework significantly outperforms existing approaches in simulation and has been successfully deployed in a real-world large-scale building environment (200m × 130m), demonstrating both high efficiency and robustness.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Planning with Language Models
• 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
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• autonomous exploration
• semantic reasoning
• local control
• hierarchical framework
• robot navigation

Innovation

• hierarchical exploration
• large language model
• reinforcement learning
• fast-slow thinking
• topological graph pruning