{"ID":2885001,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05021","arxiv_id":"2508.05021","title":"MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding","abstract":"Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs), enhanced with two human-inspired mechanisms: perspective-based active grounding, which dynamically adjusts the robot's viewpoint for improved visual inspection, and historical memory backtracking, which enables the system to retain and re-evaluate uncertain observations over time. Unlike existing approaches that passively rely on incidental visual inputs, our method actively optimizes perception and leverages memory to resolve ambiguity, significantly improving vision-language grounding in complex, unseen environments. Our framework operates in a zero-shot manner, achieving strong generalization to diverse and open-ended language descriptions without requiring labeled data or model fine-tuning. Experimental results on Habitat-Matterport 3D (HM3D) show that our method outperforms state-of-the-art approaches in language-driven object navigation. We further demonstrate its practicality through real-world deployment on a quadruped robot, achieving robust and effective navigation performance.","short_abstract":"Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs), enhanced with two human-inspired mechanisms: perspective-based active grounding, whi...","url_abs":"https://arxiv.org/abs/2508.05021","url_pdf":"https://arxiv.org/pdf/2508.05021v1","authors":"[\"Weifan Zhang\",\"Tingguang Li\",\"Yuzhen Liu\"]","published":"2025-08-07T04:15:08Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}