丘腾海

丘腾海  /  

  • 职  称: 副高级
  • 邮  编: 100190
  • 电子邮件: tenghai.qiu@ia.ac.cn
  • 部门/实验室: 复杂系统认知与决策重点实验室
  • 通讯地址: 北京市海淀区中关村东路95号

个人简历

2024.09~至今,中国科学院自动化研究所,副研究员

2018.04~2024.9,中国科学院自动化研究所,助理研究员

2016.04~2018.10,中国科学院自动化研究所,助理工程师

研究方向

群体智能决策、无人集群博弈智能决策、多无人机/车等机器人集群任务智能规划,重点涉及多智能体强化学习、大模型、运筹优化等。

承担科研项目情况

(1)集群智能协同决策技术,主持,国家级,2024.09~2025.09;

(2)异构集群行动方案生成技术,主持,国家级,2022.11~2024.06;

(3)拒止环境下在线目标分配技术,主持,航天科技横向课题,2021.08~2022.08;

(4)无人机“蜂群”智能协同关键技术,主持,中国科学院基金,2020.07~2021.06;

(5)京东物流飞行平台软件开发,主持,横向课题,2020.06~2021.09;

(6)任务规划与决策技术,主持,中国兵器横向课题,2019.03~2020.11;

(7)"蜂群”系统群智实时推理与对抗技术,核心骨干,科技创新2030“新一代人工智能”重大项目课题,2019.12~2023.05;

(8)蜂群系统关键技术集成验证与应用示范,核心骨干,科技创新2030“新一代人工智能”重大项目课题,2019.12~2023.12。

代表论著

[1]Lexing Wang, Tenghai Qiu*, Zhiqiang Pu, Jianqiang Yi, et al. Hedonic Coalition Formation for Distributed Task Allocation in Heterogeneous Multi-agent System[J]. International Journal of Control, Automation and Systems, 2024, 22(4): 1212-1224.

[2]Qingxu Fu, Tenghai Qiu*, Jianqiang Yi, Zhiqiang Pu, et al. A Policy Resonance Approach to Solve the Problem of Responsibility Diffusion in Multiagent Reinforcement Learning[J]. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024.

[3]Qingxu Fu and Tenghai Qiu* and Jianqiang Yi and Zhiqiang Pu and Xiaolin Ai, Self-Clustering Hierarchical Multi-Agent Reinforcement Learning with Extensible Cooperation Graph[J]. IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), 2024.

[4]Tenghai Qiu*, Zhiqiang Pu, Tianle Zhang, Jianqiang Yi, et al: Multi-Missile Cooperative Attack using Attention-Based Reinforcement Learning, 2023 International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC), Shenzhen, China, October 20-22, pp.148-153. 2023.

[5]Qingxu Fu, Tenghai Qiu*, Zhiqiang Pu, Jianqiang Yi, et al: Learning Superior Cooperative Policy in Competitive Multi-team Reinforcement Learning, 2023 International Joint Conference on Neural Networks (IJCNN 2023), Gold Coast, Australia, June 18-23, 2023. DOI: 10.1109/IJCNN54540.2023.10191422.  2023.

[6]Lexing Wang, Tenghai Qiu*, Zhiqiang Pu, Jianqiang Yi, Jinying Zhu, and Yanjie Zhao. "A Decision-making Method for Swarm Agents in Attack-defense Confrontation." IFAC-PapersOnLine 56, no. 2 (2023): 7858-7864.

[7]Qingxu Fu, Tenghai Qiu*, Jianqiang Yi, Zhiqiang Pu, and Wanmai Yuan: A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning, 2022 International Joint Conference on Neural Networks (IJCNN2022), Padua, Italy, July 18-23, 2022.

[8]Qingxu Fu, Tenghai Qiu*, Jianqiang Yi, Zhiqiang Pu, and Shiguang Wu: Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems, Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-2022), Vancouver, Canada, February 22 - March 1, 2022, pp.9341-9349.

[9]丘腾海*, 胡佳斌, 蒲志强, and 易建强. "通信拒止环境下的导弹集群多目标分配与决策方法." 航天控制 40, no. 6 (2022): 30-38.

[10]Shiguang Wu, Tenghai Qiu*, Zhiqiang Pu, and Jianqiang Yi: Multi-agent Collaborative Learning with Relational Graph Reasoning in Adversarial Environments, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021), Prague, Czech, Sept 27 - Oct 1, 2021, pp.5596-5602.

[11]Huimu Wang, Tenghai Qiu*, Zhen Liu, Zhiqiang Pu, Jianqiang Yi, and Wanmai Yuan: Multi-Agent Cognition Difference Reinforcement Learning for Multi-Agent Cooperation, 2021 International Joint Conference on Neural Networks (IJCNN2021), Shenzhen, China, July 18-22, 2021.

[12]Huimu Wang, Tenghai Qiu*, Zhen Liu, Zhiqiang Pu, and Jianqiang Yi: Multi-agent Formation Control with Obstacles Avoidance under Restricted Communication through Graph Reinforcement Learning, The 21st World Congress of the International Federation of Automatic Control (IFAC 2020), Berlin, Germany, July 12-17, 2020. IFAC PapersOnLine 53-2 (2020) 8150-8156.

获奖及荣誉

(1)2020全国多智能体对抗博弈挑战赛异构组第1名(共180个单位、273支队伍)

(2)2021全国空中智能博弈大赛第1名(共108支队伍)

专利成果

[1]一种基于专注网络的集群对抗方法及装置,2023年,发明专利,第1作者,授权号:CN114118400B

[2]基于多智能体协作系统的深度强化学习方法和装置,2022年,发明专利,第1作者,授权号:CN114792133B

[3]基于注意力网络的无人集群对抗方法、装置及无人设备,2022年,发明专利,第1作者,授权号:CN114815904B

[4]无人集群对抗方法、装置、电子设备及存储介质,2022年,发明专利,第1作者,授权号:CN114815900B

[5]一种基于改进A*算法和深度强化学习的无人车路径规划方法,2022年,发明专利,第1作者,授权号:CN111780777B

[6]基于混合式架构的群体智能协同方法和系统,2021年,发明专利,第1作者,授权号:CN111830995B

[7]基于知识与数据驱动的无人车分层决策方法、系统、装置,2021年,发明专利,第1作者,授权号:CN111874007B

[8]基于连通保持约束的群体围捕方法及装置,2021年,发明专利,第1作者,授权号:CN113268893B

[9]群体对抗中智能体控制方法、装置、电子设备及存储介质,2021年,发明专利,第1作者,授权号:CN113283574B

[10] 基于角色分配的群体分布式控制方法及装置,2021年,发明专利,第1作者,授权号:CN113391556B

[11]一种松散的集群控制方法、装置、设备、介质和产品,2021年,发明专利,第1作者,授权号:CN113645317B

[12]基于知识嵌入的区域覆盖和连通保持的集群控制方法,2021年,发明专利,第1作者,授权号:CN112203291B

[13]基于强化学习的飞行器姿态控制方法、系统、装置,2021年,发明专利,第1作者,授权号:CN112198890B

[14]机器人导航方法、装置、电子设备及存储介质,2021年,发明专利,第1作者,授权号:CN113282093B