个人信息
Personal Information
联系方式
Contact Information
个人简介
Personal Profile
郭宪,现为南开大学副研究员,2009年本科毕业于华中科技大学,2016年1月博士毕业于中国科学院大学沈阳自动化研究所。2016年1月到2018年6月在南开大学计算机与控制工程学院进行博士后研究工作,2018年7月入职为南开大学人工智能学院讲师,2020年任职副研究员,并任职到现在。2020年入选第七批天津市创新人才推进计划青年科技优秀人才。主要研究方向为仿生机器人设计与智能控制、强化学习、机器人博弈。主持国家级项目3项,省部级项目1项,在国内外重要国际期刊和会议发表论文二十余篇。近年来,申请人将人工智能算法与仿生机器人的运动控制相结合,探索深度强化学习方法在仿生机器人运动控制方面的应用;与此同时,申请人对深度强化学习等智能算法进行深入研究,并积极将该算法应用到机器人博弈,无人机博弈,导弹姿态控制等领域,在智能控制、智能博弈、智能对抗方面开辟新的研究方向。
上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg上传附件
支持扩展名:.rar .zip .doc .docx .pdf .jpg .png .jpeg在研项目:
1. "面向蛇形机器人步态生成的高效安全鲁棒强化学习方法研究”,国家自然科学基金委面上项目
2. “基于深度强化学习的可变形蛇形机器人的智能运动研究”, 天津市自然科学基金委青年科学基金项目
已完成项目:
1."基于蝮蛇视觉机理的蛇形机器人目标跟踪系统研究",国家自然科学基金委青年科学基金项目61603200
近五年期刊论文(部分论文):
[1] Wei Huang , Yongchun Fang , Xian Guo , Huawang Liu ,and Lixing Liu. A Unified Motion Modeling Approach for Snake Robot’s Gaits Generated With Backbone Curve Method. IEEE TRANSACTIONS ON ROBOTICS, 2024,40:4132-4146.
[2] Lixing Liu*, Jiashun Liu*, Xian Guo,Wei Huang, Yongchun Fang, and Jianye Hao. Representation ReinforcementLearning-Based Dense Control for Point following With State Sparse Sensing of 3D Snake Robots.IEEE/ASME Transactions on Mechatronics. DOI: 10.1109/TMECH.2024.3465018, 2024
[3] Lixing Liu , Xian Guo , Wei Xi , WeiHuang , and Yongchun Fang,A Reinforcement Learning PathFollowing Strategy for Snake Robots Based on Transferable Constrained-ResidualGait Generator. IEEE Transactions on Industrial Electronics,2024,71(12):16013-16025.
[4] Fengwei Sheng, Fuxi Wan, Chaoquan Tang,Xian Guo. A Maneuverable Winding Gait for Snake Robots Based on a Delay-AwareSwing and Grasp Framework Combining Rules and Learning Methods, IEEE Roboticsand Automation Letters. 2025,10(1):311-318.
[5] Xiaojie Xu, Yunfan Wang, Xian Guo,Kuihua Huang, Xuebo Zhang. Multi-UAV air combat cooperative game based onvirtual opponent and value attention decomposition policy gradient. ExpertSystem with Applications. 2025,267:126069.
[6]W. Zhu, X.Guo, Y. Fang, and X. Zhang, A path-integral-based reinforcement Learningalgorithm for path following of an autoassembly mobile robot, IEEE Transactionson neural networks and learning systems. 2020, 31(11):4487-4499
[7] M. Zhao, X.Guo, X. Zhang, Y. Fang, Y. Ou, ASPW-DRL: assembly sequence planning forworkpieces via a deep reinforcement learning approach, Assembly Automation,2020,40(1):65-75
[8]仿生机器人运动步态控制:强化学习方法综述,智能系统学报,2020,15(1):152-159
[9]可重构模块化蛇形机器人研制及多运动模态研究,信息与控制,2020,49(1):69-77.
[10] X. Guo,W. Zhu, and Y. Fang, Guided motion planning for snake-like robots based ongeometry mechanics and HJB equation, IEEE Transactions on IndustrialElectronics, 2019, 66(9):7120-7130.
[11]方勇纯,朱威,郭宪.基于路径积分强化学习方法的蛇形机器人目标导向运动.模式识别与人工智能,2019,32(1):1-9.
[12] X. Guo, S.Ma, B. Li, and Y. Fang, A novel serpentine gait generation method forsnake-like robots based on Geometry Mechanics. IEEE/ASME Transactions onMechatronics, 2018, 23(3):1249-1258
部分会议论文:
[1]L. Liu, X. Guo, Y. Fang, Vision-based Path Following of Snake-likeRobots, ICRA2021 accepted
[2]X. Zhang, W. Xi, X. Guo, Y. Fang, B. Wang, W. Liu, J. Hao, RelationalNavigation Learning in Continuous Action Space among Crowds, ICRA2021 accepted
[3]X. Zhang, X. Guo, Y. Fang, W. Zhu, Reinforcement Learning-based HierarchicalControl for Path Following of a Salamander-like Robot, IROS2020.
[4]T. Li, J. Fan, X. Guo, M. Hao, M. Sun, Self-Tuning Attitude Control Design ofHypersonic Aircraft with Multi-Constraints Based on Soft-Constrained PI2 withAction Smooth, 2020 Chinese Automation Congress.
代表性著作:
[1] 郭宪,方勇纯, 深入浅出强化学习:原理入门, 电子工业出版社,2018.1.
[2] 郭宪,宋俊潇,方勇纯, 深入浅出强化学习:编程实战, 电子工业出版社,2020.3
文件上传中...