CORE Planner: Contextual-memory Oriented Reinforcement-learning in Unknown Environments for Robot Navigation

2026-06-28

AI Summary

This work addresses key challenges in autonomous robot navigation within unknown environments—namely, the lack of environmental memory, reliance on handcrafted rules, and difficulties in sim-to-real transfer—by proposing a novel approach that integrates classical planning with reinforcement learning. The method employs a sparse visibility graph for structured environment modeling and leverages a Transformer network to enable global scene understanding and contextual memory. Trained solely on visual inputs, the system achieves zero-shot transfer to real-world settings without fine-tuning. In complex environments, it reduces path length by 13% compared to FAR Planner and by up to 48% against learning-based baselines, while successfully navigating real-world scenes without human intervention.

Abstract

Autonomous navigation in unknown environments requires a robot to efficiently reach a predefined goal while exploring without prior maps. Although progress has been made in this area, most existing works still rely on traditional planning methods with hand-crafted rules, while learning-based methods often suffer from limited environmental memory and challenges in simulation-to-real (sim-to-real) transfer. To overcome these limitations, we propose a Contextual-memory Oriented Reinforcement-learning (CORE) planner for robot navigation in unknown environments. The proposed CORE planner effectively combines the core advantages of traditional and learning-based methods. Specifically, our method uses a sparse visibility graph for structured environment representation, reducing the computational overhead of dense grid maps, and employs a Transformer network to achieve a holistic environmental understanding, thereby significantly improving navigation efficiency. Moreover, we introduce a visibility graph-based graph sparsification method and a contextual memory mechanism, which alleviates local optima and enhances computational performance in large-scale scenes. Finally, our approach achieves zero-shot sim-to-real transfer after training solely on image-based environments, requiring no fine-tuning. Experimental results show that CORE Planner consistently outperforms state-of-the-art methods, including the traditional FAR Planner and all learning-based baselines, across representative environments, reducing travel distance by 13\% over traditional FAR Planner and by up to 48\% relative to learning-based baselines, with larger gains observed in more complex environments. In real-world scenarios, CORE successfully navigates without human intervention, showcasing zero-shot sim-to-real transfer. Code is available at https://github.com/BBD00/core_planner.

Problem

• autonomous navigation
• unknown environments
• sim-to-real transfer
• environmental memory
• robot navigation

Innovation

• Contextual Memory
• Reinforcement Learning
• Visibility Graph
• Zero-shot Sim-to-Real Transfer
• Transformer-based Navigation