科学研究情况
1、承担项目情况
1. 辽宁省博士科研启动基金计划项目：面向拒止环境下失能无人艇的类脑认知导航具身进化研究，2025-08至2027-07，主持。
2. 辽宁省2023年第一批中央引导地方科技发展资金项目：类脑认知智慧导盲场景创新应用基础研究，2023-01至2023-12，参与。
3. 国家自然科学基金项目：类脑双通路自主强化学习建模方法及其在水下潜航器中的应用研究，2022-01至2025-12，参与。
4. 辽宁省航运联合基金项目：基于深度感知的水下目标智能搜救关键技术研究，2021-01至2022-12，参与。
2、发表学术论文情况
[1] Naiyao Wang, Bo Zhang, Haixu Chi, Hua Wang, Seán McLoone and Hongbo Liu, DUEL: Depth visUal Ego-motion Learning for Autonomous Robot Obstacle Avoidance, International Journal of Robotics Research, 2024, 43(3): 305-329.
[2] Naiyao Wang, Changdong Zhou, Rongfeng Zhu, Bo Zhang, Ye Wang and Hongbo Liu, SOFT: Self-Supervised Sparse Optical Flow Transformer for Video Stabilization via Quaternion, Engineering Applications of Artificial Intelligence, 2024, 130: 107725.
[3] Naiyao Wang, Houhua Shao, Xirong Fu, Xinqiang Xie, Hongbo Liu, BI-PIPE: Brain-inspired brisk inference pathway intention prediction for embodied navigation of unmanned surface vessel, Ocean Engineering, 2026, 359: 125879.
[4] Dafeng Wang, Hongbo Liu, Naiyao Wang, Yiyang Wang, Hua Wang and Seán McLoone, SEEM: A sequence entropy energy-based model for pedestrian trajectory all-then-one prediction, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 1070-1086.
[6] Changdong Zhou, Ruofan Hu, Naiyao Wang, Ke Song, Hongbo Liu, HIVE: A Hypergraph-based game-theoretic Interactive Value decomposition Engine for multi-lateral agents collaboration, Neural Networks, 2026: 109103.
[5] Dafeng Wang, Qian Ma, Naiyao Wang, Xuanzhe Fan, Mingyu Lu and Hongbo Liu, AONet: Active Offset Network for crowd flow prediction, Engineering Applications of Artificial Intelligence, 2021, 97: 104022.
[7] Shaoyang Qiu, Hongxiang Ren, Naiyao Wang and Hongbo Liu, 3D motion model for the freefall lifeboat during its launching from a moving ship, Ocean Engineering, 2023, 278:114363.
[8] Bo Zhang, Naiyao Wang, Zheng Zhao, Ajith Abraham and Hongbo Liu, Crowd counting based on attention-guided multi-scale fusion networks, Neurocomputing, 2021, 451: 12-24.
3、获得授权专利情况
1、基于转换器模型进行视听模态融合的具身视听导航方法
2、一种类脑快慢双通路无人自主决策方法
3、一种模型-数据混合驱动固定翼无人机自主认知避障方法
4、一种基于非监督的卷积神经网络单目场景深度估计方法
5、一种基于六自由度运动平台的机器视觉自主调节与稳定增强系统及构建方法
6、基于压缩代码属性图和边类型差异化处理的漏洞检测方法
7、一种面向工业物联网的高效异构联邦学习方法
4、出版学术专著情况
