HELM: Human-Preferred Exploration with Language Models

2025-03-10

AI Summary

Autonomous robotic exploration in dynamic, unknown environments struggles to adaptively respond to diverse human preferences—such as region prioritization or efficiency–completeness trade-offs—without manual intervention. Method: This paper proposes the first end-to-end framework that deeply integrates large language models (LLMs) into the exploration closed loop. It synergistically combines LLM-based semantic understanding, natural language instruction parsing, real-time semantic mapping, and motion planning to enable zero-shot, retraining-free preference modulation—directly translating human natural language intent into adaptive exploration policies. Results: In multi-scenario experiments, the method achieves task success rates comparable to state-of-the-art traditional approaches while enabling millisecond-level preference switching. Its core contribution is the first generalizable, fine-tuning-free language-to-exploration-policy mapping mechanism, eliminating reliance on hand-crafted parameters or offline training—thereby significantly enhancing human–robot collaboration flexibility and practicality.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Learning Human Values and Preferences

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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

Abstract

In autonomous exploration tasks, robots are required to explore and map unknown environments while efficiently planning in dynamic and uncertain conditions. Given the significant variability of environments, human operators often have specific preference requirements for exploration, such as prioritizing certain areas or optimizing for different aspects of efficiency. However, existing methods struggle to accommodate these human preferences adaptively, often requiring extensive parameter tuning or network retraining. With the recent advancements in Large Language Models (LLMs), which have been widely applied to text-based planning and complex reasoning, their potential for enhancing autonomous exploration is becoming increasingly promising. Motivated by this, we propose an LLM-based human-preferred exploration framework that seamlessly integrates a mobile robot system with LLMs. By leveraging the reasoning and adaptability of LLMs, our approach enables intuitive and flexible preference control through natural language while maintaining a task success rate comparable to state-of-the-art traditional methods. Experimental results demonstrate that our framework effectively bridges the gap between human intent and policy preference in autonomous exploration, offering a more user-friendly and adaptable solution for real-world robotic applications.

Problem

• Adapting robots to human exploration preferences in dynamic environments.
• Integrating LLMs for intuitive natural language control in robotic exploration.
• Bridging human intent and policy preference in autonomous robotic systems.

Innovation

• LLM-based human-preferred exploration framework
• Natural language control for robot preferences
• Seamless integration of LLMs with mobile robots