Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22923v1</id>\n    <title>WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents</title>\n    <updated>2026-02-26T12:12:40Z</updated>\n    <link href='https://arxiv.org/abs/2602.22923v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22923v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>While autonomous navigation has achieved remarkable success in passive perception (e.g., object detection and segmentation), it remains fundamentally constrained by a void in knowledge-driven, interactive environmental cognition. In the high-stakes domain of maritime navigation, the ability to bridge the gap between raw visual perception and complex cognitive reasoning is not merely an enhancement but a critical prerequisite for Autonomous Surface Vessels to execute safe and precise maneuvers. To this end, we present WaterVideoQA, the first large-scale, comprehensive Video Question Answering benchmark specifically engineered for all-waterway environments. This benchmark encompasses 3,029 video clips across six distinct waterway categories, integrating multifaceted variables such as volatile lighting and dynamic weather to rigorously stress-test ASV capabilities across a five-tier hierarchical cognitive framework. Furthermore, we introduce NaviMind, a pioneering multi-agent neuro-symbolic system designed for open-ended maritime reasoning. By synergizing Adaptive Semantic Routing, Situation-Aware Hierarchical Reasoning, and Autonomous Self-Reflective Verification, NaviMind transitions ASVs from superficial pattern matching to regulation-compliant, interpretable decision-making. Experimental results demonstrate that our framework significantly transcends existing baselines, establishing a new paradigm for intelligent, trustworthy interaction in dynamic maritime environments.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <published>2026-02-26T12:12:40Z</published>\n    <arxiv:comment>11 pages,8 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Runwei Guan</name>\n    </author>\n    <author>\n      <name>Shaofeng Liang</name>\n    </author>\n    <author>\n      <name>Ningwei Ouyang</name>\n    </author>\n    <author>\n      <name>Weichen Fei</name>\n    </author>\n    <author>\n      <name>Shanliang Yao</name>\n    </author>\n    <author>\n      <name>Wei Dai</name>\n    </author>\n    <author>\n      <name>Chenhao Ge</name>\n    </author>\n    <author>\n      <name>Penglei Sun</name>\n    </author>\n    <author>\n      <name>Xiaohui Zhu</name>\n    </author>\n    <author>\n      <name>Tao Huang</name>\n    </author>\n    <author>\n      <name>Ryan Wen Liu</name>\n    </author>\n    <author>\n      <name>Hui Xiong</name>\n    </author>\n  </entry>"
}