WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guan, Runwei, Liang, Shaofeng, Ouyang, Ningwei, Fei, Weichen, Yao, Shanliang, Dai, Wei, Ge, Chenhao, Sun, Penglei, Zhu, Xiaohui, Huang, Tao, Liu, Ryan Wen, Xiong, Hui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914353098260480
author Guan, Runwei
Liang, Shaofeng
Ouyang, Ningwei
Fei, Weichen
Yao, Shanliang
Dai, Wei
Ge, Chenhao
Sun, Penglei
Zhu, Xiaohui
Huang, Tao
Liu, Ryan Wen
Xiong, Hui
author_facet Guan, Runwei
Liang, Shaofeng
Ouyang, Ningwei
Fei, Weichen
Yao, Shanliang
Dai, Wei
Ge, Chenhao
Sun, Penglei
Zhu, Xiaohui
Huang, Tao
Liu, Ryan Wen
Xiong, Hui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22923
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents
Guan, Runwei
Liang, Shaofeng
Ouyang, Ningwei
Fei, Weichen
Yao, Shanliang
Dai, Wei
Ge, Chenhao
Sun, Penglei
Zhu, Xiaohui
Huang, Tao
Liu, Ryan Wen
Xiong, Hui
Computer Vision and Pattern Recognition
Robotics
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.
title WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2602.22923