基本信息
邢登鹏 多模态人工智能系统全国重点实验室 中国科学院自动化研究所
电子邮件: dengpeng.xing@ia.ac.cn
通信地址: 北京市海淀区中关村东路95号
邮政编码: 100090
研究领域
机器人控制,类脑智能,因果强化学习
招生信息
希望招收能对科研保持激情、有志于脚踏实地做出带有自己标签的学术成就的学生;同时也希望你具有较好的编程能力和数学功底。
招生专业
081101-控制理论与控制工程081104-模式识别与智能系统
招生方向
机器人控制类脑智能因果强化学习
教育背景
2008-12--2009-12 美国卡内基梅隆大学机器人所 访问学者2006-03--2010-07 上海交通大学自动化系 工学博士2003-09--2006-03 天津大学机械制造及其自动化系 工学硕士1998-09--2002-07 天津大学机械电子工程系 工学学士
工作经历
工作简历
2022-11~现在, 中国科学院自动化研究所, 研究员2013-10~2022-10,中国科学院自动化研究所, 副研究员2012-11~2013-10,中国科学院自动化研究所, 助理研究员2010-11~2012-11,上海交通大学, 博士后
教授课程
机器人学机器人机构学机器人学导论
专利与奖励
专利成果
( 1 ) 模型迁移方法、装置, 发明专利, 2021, 第 1 作者, 专利号: 202111206993.4( 2 ) 机器人控制方法、装置、电子设备及存储介质, 发明专利, 2021, 第 1 作者, 专利号: 202111122532.9( 3 ) 一种机器人控制方法、装置及存储介质, 发明专利, 2021, 第 1 作者, 专利号: 202111113736.6( 4 ) 数据集生成方法、装置、电子设备及存储介质, 发明专利, 2021, 第 1 作者, 专利号: 202111105029.2( 5 ) 轮腿机器人的自稳定控制方法、系统、装置, 发明专利, 2020, 第 1 作者, 专利号: CN110764413A( 6 ) 多路真空正、负压输出控制装置, 发明专利, 2014, 第 1 作者, 专利号: CN103499986A( 7 ) 一种多路显微视觉标定系统及方法, 发明专利, 2014, 第 1 作者, 专利号: CN103544701A
出版信息
发表论文
[1] 余忠蔚, 阮景晴, 邢登鹏. Learning causal dynamics models in object-oriented environments. International Conference on Machine Learning. 2024, 第 3 作者 通讯作者 [2] Xing, Dengpeng, Yang, Yiming, Tielin Zhang, Bo Xu. A Brain-Inspired Approach for Probabilistic Estimation and Efficient Planning in Precision Physical Interaction. IEEE Transactions on Cybernetics[J]. 2023, 第 1 作者[3] Jingqing Ruan, 王开申, Qingyang zhang, Xing, Dengpeng, 徐波. Learning top-K subtask planning tree based on discriminative representation pre-training for decision-making. Machine Intelligence Research[J]. 2023, 第 4 作者 通讯作者 [4] 余忠蔚, 阮景晴, Xing, Dengpeng. Explainable reinforcement learning via a causal world model. International Joint Conference on Artificial Intelligence. 2023, 第 3 作者 通讯作者 [5] Xuantang Xiong, Linghui Meng, Jingqing Ruan, Qingyang zhang, guoqi li, Xing, Dengpeng, 徐波. Task-prompt generalized world model in multi-environment offline reinforcement learning. European Conference on Artificial Intelligence. 2023, 第 6 作者 通讯作者 [6] Xing, Dengpeng, 杨依明, 王泽昌, 李佳乐, 徐波. Generalized robot dynamics learning and Gen2Real transfer. IEEE/RSJ International Conference on Intelligent Robots and Systems. 2023, 第 1 作者[7] Qingyang zhang, 王开申, Jingqing Ruan, Yiming Yang, Xing, Dengpeng, 徐波. Enhancing multi-agent coordination via dual-channel consensus. Machine Intelligence Research[J]. 2023, 第 5 作者[8] 王开申, Jingqing Ruan, Qingyang zhang, Xing, Dengpeng. Efficient hierarchical reinforcement learning via mutual information constrained subgoal discovery. International Conference on Neural Information Processing. 2023, 第 4 作者 通讯作者 [9] 孟令辉, 阮景晴, 熊炫堂, 李熙云, Xi Zhang, Xing, Dengpeng, 徐波. M3: Modularization for multi-task and multi-agent offline pre-training. International Conference on Autonomous Agents and Multiagent Systems. 2023, 第 6 作者 通讯作者 [10] 张清扬, 杨依明, 阮景晴, 熊炫堂, Xing, Dengpeng, 徐波. Balancing exploration and exploitation in hierarchical reinforcement learning via latent landmark graphs. International Joint Conference on Neural Networks. 2023, 第 5 作者 通讯作者 [11] Linghui Meng, Muning Wen, Chenyang Le, Xiyun Li, Dengpeng Xing, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Yaodong Yang, Bo Xu. Offline Pre-trained Multi-agent Decision Transformer. 机器智能研究:英文版[J]. 2023, 第 5 作者20(2): 233-248, http://lib.cqvip.com/Qikan/Article/Detail?id=7109371017.[12] Linghui Meng, Xuantang Xiong, 臧一凡, Xi Zhang, guoqi li, Xing, Dengpeng, 徐波. Filtered Observations for Model-based Multi-agent Reinforcement Learning. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. 2023, 第 6 作者 通讯作者 [13] Qingyang zhang, Kaishen Wang, Jingqing Ruan, Yiming Yang, Xing, Dengpeng, 徐波. Latent landmark graph for efficient exploration-exploitation balance in hierarchical reinforcement learning. Machine Intelligence Research[J]. 2023, 第 5 作者[14] 夏万年, Yiming Yang, Jingqing Ruan, Xing, Dengpeng, 徐波. Cardsformer: Grounding language to learn a generalizable policy in hearthstone. European Conference on Artificial Intelligence. 2023, 第 4 作者 通讯作者 [15] Yiming Yang, Dengpeng Xing, Bo Xu. Efficient spatiotemporal transformer for robotic reinforcement learning. IEEE ROBOTICS AND AUTOMATION LETTERS[J]. 2022, 第 2 作者 通讯作者 7(3): [16] Jingqing Ruan, Yali Du, Xuantang Xiong, Xing, Dengpeng, Xiyun Li, Linghui Meng, Haifeng Zhang, Jun Wang, Bo Xu. GCS: Graph-Based Coordination Strategy for Multi-Agent Reinforcement Learning. International Joint Conference on Autonomous Agents and Multi-agent Systems (AAMAS). 2022, 第 4 作者[17] Xing, Dengpeng, Jiale Li, Tielin zhang, Bo Xu. A brain-inspired approach for collision-free movement planning in the small operational space. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS[J]. 2022, 第 1 作者[18] Linghui Meng, Jingqing Ruan, Xing, Dengpeng, bo xu. Learning in bi-level Markov games. International Joint Conference on Neural Networks. 2022, 第 3 作者 通讯作者 [19] Jingqing Ruan, Linghui Meng, Xuantang Xiong, Xing, Dengpeng, Bo Xu. Learning Multi-agent Action Coordination via Electing First-move Agent. International Conference on Automated Planning and Scheduling. 2022, 第 4 作者 通讯作者 [20] Xing, Dengpeng, Wannian Xia, Bo Xu. Kinematics learning of massive heterogeneous serial robots. International conference on robotics & automation (ICRA). 2022, 第 1 作者[21] Xing, Dengpeng, Liu, Fangfang, Xu, De. Joint Alignment and Simultaneous Insertion of Multiple Objects in Precision Assembly. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2021, 第 1 作者17(1): 230-239, https://www.webofscience.com/wos/woscc/full-record/WOS:000587719200021.[22] Xing, Dengpeng, Liu, Xiwei, Liu, Fangfang, Xu, De. Efficient Insertion Strategy for Precision Assembly With Uncertainties Using a Passive Mechanism. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2021, 第 1 作者17(2): 1263-1273, http://dx.doi.org/10.1109/TII.2020.2986805.[23] Xing, Dengpeng, Liu, Fangfang, Xu, De, Xu, Bo. Simultaneous Control in Belief Space for Circular Insertion in Precision Assembly. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2021, 第 1 作者17(3): 1842-1851, http://dx.doi.org/10.1109/TII.2020.2998165.[24] Qin, Fangbo, Zhang, Dapeng, Xing, Dengpeng, Xu, De, Li, Jianquan. Laser Beam Pointing Control With Piezoelectric Actuator Model Learning. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS[J]. 2020, 第 3 作者50(3): 1024-1034, http://dx.doi.org/10.1109/TSMC.2017.2754863.[25] 吴班, 邢登鹏. 面向细长形物体的精密运动规划. 华中科技大学学报:自然科学版[J]. 2020, 第 2 作者48(11): 43-47,59, http://lib.cqvip.com/Qikan/Article/Detail?id=7103435940.[26] Xing, Dengpeng, Liu, Fangfang, Xu, De. Coordinated Motion Planning of Independent Manipulators in Precision Manipulation. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2020, 第 1 作者16(11): 6933-6942, https://www.webofscience.com/wos/woscc/full-record/WOS:000554904700019.[27] Xing, Dengpeng, Liu, Fangfang, Xu, De. Efficient Coordinated Control Strategy to Handle Randomized Inclination in Precision Assembly. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2020, 第 1 作者16(9): 5814-5824, https://www.webofscience.com/wos/woscc/full-record/WOS:000542966300017.[28] Liu, Song, Li, YouFu, Xing, Dengpeng. Sensing and Control for Simultaneous Precision Peg-in-Hole Assembly of Multiple Objects. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING[J]. 2020, 第 3 作者17(1): 310-324, https://www.webofscience.com/wos/woscc/full-record/WOS:000507640900024.[29] Xing, Dengpeng, Lv, Yan, Liu, Song, Xu, De, Liu, Fangfang. Efficient Insertion of Multiple Objects Parallel Connected by Passive Compliant Mechanisms in Precision Assembly. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2019, 第 1 作者15(9): 4878-4887, https://www.webofscience.com/wos/woscc/full-record/WOS:000489584600004.[30] Xing, Dengpeng, Liu, Fangfang, Liu, Song, Xu, De. Efficient Insertion of Partially Flexible Objects in Precision Assembly. IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING[J]. 2019, 第 1 作者16(2): 706-715, [31] Liu, Song, Xing, Dengpeng, Li, YouFu, Zhang, Jianwei, Xu, De. Robust Insertion Control for Precision Assembly With Passive Compliance Combining Vision and Force Information. IEEE-ASME TRANSACTIONS ON MECHATRONICS[J]. 2019, 第 2 作者24(5): 1974-1985, https://www.webofscience.com/wos/woscc/full-record/WOS:000493174900007.[32] Xing, Dengpeng, Liu, Fangfang, Liu, Song, Xu, De. Efficient Collision Detection and Detach Control for Convex Prisms in Precision Manipulation. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS[J]. 2018, 第 1 作者14(12): 5316-5326, http://ir.ia.ac.cn/handle/173211/25653.[33] Liu, Song, Li, YouFu, Xing, Dengpeng, Xu, De, Su, Hu. An Efficient Insertion Control Method for Precision Assembly of Cylindrical Components. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS[J]. 2017, 第 3 作者64(12): 9355-9365, https://www.webofscience.com/wos/woscc/full-record/WOS:000413946800018.[34] Xing, Dengpeng, Liu, Fangfang, Liu, Song, Xu, De. Motion Control for Cylindrical Objects in Microscope's View Using a Projection Method-II: Collision Avoidance With Reduced Dimensional Guidance. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS[J]. 2017, 第 1 作者64(7): 5534-5544, https://www.webofscience.com/wos/woscc/full-record/WOS:000403011200029.[35] Qin, FangBo, Xu, De, Xing, Dengpeng, Zhang, ZhengTao. An Active Radial Compliance Method with Anisotropic Stiffness Learning for Precision Assembly. INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING[J]. 2017, 第 3 作者 通讯作者 18(4): 471-478, https://www.webofscience.com/wos/woscc/full-record/WOS:000399128900001.[36] Xing, Dengpeng, Liu, Fangfang, Liu, Song, Xu, De. Motion Control for Cylindrical Objects in Microscope's View Using a Projection Method-I: Collision Detection and Detach Control. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS[J]. 2017, 第 1 作者64(7): 5524-5533, https://www.webofscience.com/wos/woscc/full-record/WOS:000403011200028.[37] Xing, Dengpeng, Liu, Fangfang, Qin, Fangbo, Xu, De. Coordinated Insertion Control for Inclined Precision Assembly. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS[J]. 2016, 第 1 作者63(5): 2990-2999, https://www.webofscience.com/wos/woscc/full-record/WOS:000374164600032.[38] Xing, Dengpeng, Xu, De, Liu, Fangfang, Li, Haipeng, Zhang, Zhengtao. Precision Assembly Among Multiple Thin Objects With Various Fit Types. IEEE-ASME TRANSACTIONS ON MECHATRONICS[J]. 2016, 第 1 作者21(1): 364-378, https://www.webofscience.com/wos/woscc/full-record/WOS:000372013900035.[39] 李海鹏, 邢登鹏, 张正涛, 徐德, 张大朋. 宏微结合的多机械手微装配机器人系统. 机器人[J]. 2015, 第 2 作者37(1): 35-42, [40] Xing, Dengpeng, Xu De, Liu Fangfang. Collision Detection for Blocking Cylindrical Objects. 2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)[J]. 2015, 第 1 作者4798-4803, [41] Xing, Dengpeng, Su, Jianbo. Joint role exploration in sagittal balance by optimizing feedback gains. ROBOTICA[J]. 2015, 第 1 作者33(1): 127-139, https://www.webofscience.com/wos/woscc/full-record/WOS:000346922000007.[42] Xing, Dengpeng, Xu, De, Li, Haipeng. A Sequence of Micro-assembly for Irregular Objects Based on a Multiple Manipulator Platform. 2014 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2014)[J]. 2014, 第 1 作者761-766, [43] Xing, Dengpeng, Xu, De, Li, Haipeng, Luo, Liyan, IEEE. Active Calibration and Its Applications on Micro-operating Platform with Multiple Manipulators. 2014 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)[J]. 2014, 第 1 作者5455-5460, [44] Xing, Dengpeng, Su, Jianbo. Optimal Parametric Controller for Perturbed Balance and Walking. 2012 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA). 2012, 第 1 作者5404-5409, [45] Xing, Dengpeng, Su, J, Liu, Y, Zhong, J. Robust approach for humanoid joint control based on a disturbance observer. IET CONTROL THEORY AND APPLICATIONS[J]. 2011, 第 1 作者 通讯作者 5(14): 1630-1636, https://www.webofscience.com/wos/woscc/full-record/WOS:000294889500006.[46] Xing Dengpeng, Liu Xu. Multiple Balance Strategies for Humanoid Standing Control. 自动化学报[J]. 2011, 第 1 作者37(2): 228-233, http://lib.cqvip.com/Qikan/Article/Detail?id=36730195.[47] 邢登鹏. Walking controllers under perturbations. IEEE International Conference on Systems, Man, and Cybernetics. 2011, 第 1 作者[48] Xing, Dengpeng, Atkeson, Christopher G, Su, Jianbo, Stephens, Benjamin J, IEEE. Gain Scheduled Control of Perturbed Standing Balance. IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010). 2010, 第 1 作者 通讯作者 4063-4068, [49] Xing Dengpeng, Su Jianbo. Controller Parameter Optimization for Multiple Balance Strategies. PROCEEDINGS OF THE 29TH CHINESE CONTROL CONFERENCE. 2010, 第 1 作者 通讯作者 3193-3198, [50] Xing, Dengpeng, Su, Jianbo. MOTION GENERATION FOR THE UPPER BODY OF HUMANOID ROBOT. INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS[J]. 2010, 第 1 作者 通讯作者 7(2): 281-294, https://www.webofscience.com/wos/woscc/full-record/WOS:000278423200004.[51] Xing, Dengpeng, Jianbo Su. Arm/trunk motion generation for humanoid robot. 中国科学:信息科学(英文版)[J]. 2010, 第 1 作者1603-1612, http://lib.cqvip.com/Qikan/Article/Detail?id=34517751.[52] Xing, Dengpeng, Su, Jianbo, IEEE. Motion Generation for the Upper Body of Humanoid Robot. PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009). 2009, 第 1 作者 通讯作者 6064-6069, [53] 邢登鹏. Feedback controller parameter optimization for standing balance. Dynamic Walking. 2009, 第 1 作者
科研活动
科研项目
( 1 ) 微装配智能学习与控制策略研究, 负责人, 国家任务, 2014-01--2016-12( 2 ) 基于深度增强学习和技能学习的微装配机器人学习与控制研究, 负责人, 国家任务, 2017-01--2020-12( 3 ) 异型零件精密微装配设备研制, 参与, 国家任务, 2012-01--2017-12( 4 ) xx机器人的自稳定控制技术, 负责人, 国家任务, 2018-11--2019-10( 5 ) 自主智能体灵巧精准操作学习方法研究, 参与, 国家任务, 2019-10--2023-10( 6 ) 基于脉冲神经网络的类脑控制研究, 负责人, 中国科学院计划, 2020-08--2022-12( 7 ) 面向刚、柔、软体的高柔顺微操作技能学习与控制策略研究, 负责人, 国家任务, 2021-01--2024-12( 8 ) 机器人脉冲神经网络控制, 负责人, 中国科学院计划, 2020-11--2023-10( 9 ) 对抗演练场人机混合智能进化技术, 负责人, 国家任务, 2023-01--2025-12
指导学生
已指导学生
刘希伟 硕士研究生 081101-控制理论与控制工程
李佳乐 硕士研究生 081203-计算机应用技术
现指导学生
余忠蔚 硕士研究生 085404-计算机技术
王开申 硕士研究生 081203-计算机应用技术
管宏阳 硕士研究生 085404-计算机技术
王泽昌 硕士研究生 081203-计算机应用技术
张一博 硕士研究生 081104-模式识别与智能系统