壹号娱乐-com

教育与工作经历

1998.9-2002.7 北京理工大学自动控制系自动化专业 学士

2002.9-2007.3 壹号娱乐模式识别与智能系统 博士

2007.4至今 壹号娱乐模式识别与智能系统研究所 教师，历任讲师、副教授、教授、特聘教授、博导

 

研究方向

1.智能控制与协同控制

2.智能系统与智能决策

3.空间智能与视觉理解

近5年承担的科研项目

主持完成国家重点研发计划等项目10余项。

代表性学术论文

1.Gan M, Zhang Y*. Content Temporal Relation Network for temporal action proposal generation[J]. Pattern Recognition, 2024, 149: 110245.

2.Gan M*, Liu J, He Y, et al. Keyframe Selection Via Deep Reinforcement Learning for Skeleton-Based Gesture Recognition[J]. IEEE Robotics and Automation Letters, 2023.

3.Gan M, Zhang Y*. Temporal attention-pyramid pooling for temporal action detection[J]. IEEE Transactions on Multimedia, 2022.

4.Gan M, He Y*. Adaptive depth-aware visual relationship detection[J]. Knowledge-Based Systems, 2022

5.Hou X, Gan M*, Wu W, et al. Predatory-imminence-continuum-inspired graph reinforcement learning for interactive motion planning in dense traffic[J]. Expert Systems with Applications, 2025.

6.Hou X, Gan M*, Wu W, et al. Interactive Motion Planning Using Genetic-Enhanced Reinforcement Learning with Backup Strategy[J]. IEEE Transactions on Vehicular Technology, 2025.

7.Hou X, Gan M*, Wu W, et al. Risk-Conscious Mutations in Jump-Start Reinforcement Learning for Autonomous Racing Policy[J]. IEEE Transactions on Cybernetics, 2024.

8.Hou X, Gan M*, Wu W, et al. Risk assessment and interactive motion planning with visual occlusion using graph attention networks and reinforcement learning[J]. Advanced Engineering Informatics, 2024.

9.Hou X, Gan M*, Wu W, et al. Equipping With Cognition: Interactive Motion Planning Using Metacognitive-Attribution Inspired Reinforcement Learning for Autonomous Vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2024.

10.Hou X, Gan M*, Wu W, et al. Cross-Observability Optimistic-Pessimistic Safe Reinforcement Learning for Interactive Motion Planning with Visual Occlusion[J]. IEEE Transactions on Intelligent Transportation Systems, 2024.

11.Hou X, Gan M*, Wu W, et al. Merging planning in dense traffic scenarios using interactive safe reinforcement learning[J]. Knowledge-Based Systems, 2024.

12.Zhang X, Chen J, Gan M*. Influence Enhanced Sparse Coordination Graphs for Multi-Agent Reinforcement Learning[J]. Neural Networks, 2025.

13.Liu X, Gan M*. RDBN: Visual relationship detection with inaccurate RGB-D images[J]. Knowledge-Based Systems, 2020.

14.Zhang M, Gan M*, Chen J. Data-driven adaptive optimal control for stochastic systems with unmeasurable state[J]. Neurocomputing, 2020.

15.Zhao J, Gan M*, Zhang C. Event-triggered H∞ optimal control for continuous-time nonlinear systems using neurodynamic programming[J]. Neurocomputing, 2019.

*表示通讯作者

授权国家发明专利及出版专著

1. 甘明刚,苏绍文,王晴,等.一种基于动作管道在线关联的智联生产线行为识别方法.

2. 甘明刚,张琰,陈杰,等.一种内容时间关系网络及生成时间动作提案的方法.

3. 甘明刚,何玉轩,陈杰,等.一种自适应深度感知视觉关系的检测方法.

4. 甘明刚,刘晋廷,曹雨,等.一种基于多模态多层次注意力机制的半监督手部骨架动作识别方法.

5. 甘明刚,朱轶兵,陈杰,等.一种工业场景数据集下的图卷积视觉关系检测方法.

6. 甘明刚,夏明月,陈杰,等.一种基于数据和模型混合驱动的生产线调度方法.

7. 甘明刚,张少卿,陈杰,等.一种基于图表示学习的生产线动态调度方法.

8. 甘明刚,郭嘉,陈杰,等.一种面向多无人机的相对定位方法.

9. 甘明刚,郭嘉,陈杰,等.一种面向无人机与无人车之间的相对定位方法.

10. 甘明刚,刘晓舟,陈杰,等.一种基于RGB-D图像的视觉语义关系检测方法.

科研获奖

作为主要完成人获得国家科技进步二等奖1项、省部级一等奖2项、二等奖2项；2017年亚洲控制会议最佳论文奖，指挥与控制学会青年科学家奖等。

学术兼职

中国自动化学会理事、 “自动控制系统”北京市重点实验室主任。