第5期 于建均，等：基于动态系统的机器人模仿学习方法研究 ·1033· on Computational Intelligence and Informatics.Budapest, on locally weighted regression[C]//Proceedings of 2016 Hungary,2013:515-519. IEEE/RSJ International Conference on Intelligent Robots [6]于建均，门玉森，阮晓钢，等.基于Kinect的Nao机器人 and Systems.Daejeon.South Korea,2016:3900-3906. 动作模仿系统的研究与实现.智能系统学报，2016， [16]MCCORMICK J,VINCS K,NAHAVANDI S,et al 11(2):180-187 Teaching a digital performing agent:Artificial neural net- YU Jianjun,MEN Yusen,RUAN Xiaogang,et al.CAAI work and hidden markov model for recognising and per- transactions on intelligent systems[J].CAAI transactions forming dance movement[Cl//Proceedings of the 2014 In- on intelligent systems,2016,11(2):180-187. ternational Workshop on Movement and Computing.Par- [7]BILLARD A.CALINON S.DILLMANN R.et al.Robot is,France,2014:70. programming by demonstration[M]//SICILIANO B. [17刀]于建均，吴鹏申，左国玉，等.基于RNN的机械臂任务 KHATIB O.Springer Handbook of Robotics.Berlin, 模仿系统.北京工业大学学报，2018,44(11)：1401- Heidelberg:Springer,2008:1371-1394. 1408 [8]ATKESON C G.SCHAAL S.Learning tasks from a single YU Jianjun,WU Pengshen,ZUO Guoyu,et al.Robot arm demonstration[C]//Proceedings of International Confer- task imitation system based on RNN[].Journal of Beijing ence on Robotics and Automation.Albuquerque,NM. University of Technology,2018,44(11):1401-1408. USA,1997:1706-1712 [18]于建均，门玉森，阮晓钢，等.在书写任务中的基于轨迹 [9]MAAREF M.REZAZADEH A.SHAMAEI K.et al.A gaussian mixture framework for co-operative rehabilita- 匹配的模仿学习[.北京工业大学学报，2016,42(8) 1144-1152 tion therapy in assistive impedance-based tasks[J].IEEE journal of selected topics in signal processing,2016,10(5): YU Jianjun,MEN Yusen,RUAN Xiaogang,et al.Imita- 904-913 tion learning based on trajectory matching in the writing [10]KULIC D,TAKANO W,NAKAMURA Y.Incremental task[J].Journal of Beijing University of Technology, learning,clustering and hierarchy formation of whole 2016,42(8):11441152. body motion patterns using adaptive hidden markov [19]IJSPEERT A J,NAKANISHI J,HOFFMANN H,et al chains[J].The international journal of robotics research, Dynamical movement primitives:learning attractor mod- 2008,27(7):761-784. els for motor behaviors[J].Neural computation,2013, [11]ANTONELO E A,SCHRAUWEN B.Supervised learn- 25(2:328-373. [20]PARASCHOS A.RUECKERT E.PETERS J.et al.Mod- ing of internal models for autonomous goal-oriented ro- el-free probabilistic movement primitives for physical in- bot navigation using reservoir computing[C]//Proceed- teraction[C]//Proceedings of 2015 IEEE/RSJ Internation- ings of 2010 IEEE International Conference on Robotics al Conference on Intelligent Robots and Systems.Ham- and Automation.Anchorage,AK,USA,2010:2959- burg,Germany,2015:2860-2866. 2964。 [21]KOCH K H,CLEVER D,MOMBAUR K,et al.Learn- [12]CALINON S,BILLARD A.Incremental learning of ges- ing movement primitives from optimal and dynamically tures by imitation in a humanoid robot[Cl//Proceedings of feasible trajectories for humanoid walking[C]//Proceed- the ACM/IEEE international conference on Human-robot ings of 2015 IEEE-RAS 15th International Conference on interaction.Arlington,VA,USA,2007:255-262 Humanoid Robots.Seoul,South Korea,2015:866-873. [13]HERSCH M,GUENTER F,CALINON S,et al.Dynam- [22]KOBER J,GIENGER M,STEIL JJ.Learning movement ical system modulation for robot learning via kinesthetic primitives for force interaction tasks[Cl//Proceedings of demonstrations[J].IEEE transactions on robotics,2008. 2015 IEEE International Conference on Robotics and 246):1463-1467 Automation.Seattle,USA.2015:3192-3199. [14]SCHAAL S,ATKESON C,VIJAYAKUMAR S.Scal- [23]WIGGINS S.Introduction to applied nonlinear dynamic- able locally weighted statistical techniques for real time al systems and chaos[M].2nd ed.New York:Springer robot learning[J].Applied intelligence-special issue on Science Business Media,2003. scalable robotic applications of neural networks,2002, [24]SEEGER M.Gaussian processes for machine learning[J]. 17(1):49-60 International journal of neural systems,2004,14(2): [15]PETERNEL L,OZTOP E,BABIC J.A shared control 69-106. method for online human-in-the-loop robot learning based [25]KHANSARI-ZADEH S M.BILLARD A.BM:an iterat-on Computational Intelligence and Informatics. Budapest, Hungary, 2013: 515–519. 于建均, 门玉森, 阮晓钢, 等. 基于 Kinect 的 Nao 机器人 动作模仿系统的研究与实现 [J]. 智能系统学报, 2016, 11(2): 180–187. YU Jianjun, MEN Yusen, RUAN Xiaogang, et al. CAAI transactions on intelligent systems[J]. CAAI transactions on intelligent systems, 2016, 11(2): 180–187. [6] BILLARD A, CALINON S, DILLMANN R, et al. Robot programming by demonstration[M]//SICILIANO B, KHATIB O. Springer Handbook of Robotics. Berlin, Heidelberg: Springer, 2008: 1371−1394. [7] ATKESON C G, SCHAAL S. Learning tasks from a single demonstration[C]//Proceedings of International Confer￾ence on Robotics and Automation. Albuquerque, NM, USA, 1997: 1706−1712. [8] MAAREF M, REZAZADEH A, SHAMAEI K, et al. A gaussian mixture framework for co-operative rehabilita￾tion therapy in assistive impedance-based tasks[J]. IEEE journal of selected topics in signal processing, 2016, 10(5): 904–913. [9] KULIĆ D, TAKANO W, NAKAMURA Y. Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden markov chains[J]. The international journal of robotics research, 2008, 27(7): 761–784. [10] ANTONELO E A, SCHRAUWEN B. Supervised learn￾ing of internal models for autonomous goal-oriented ro￾bot navigation using reservoir computing[C]//Proceed￾ings of 2010 IEEE International Conference on Robotics and Automation. Anchorage, AK, USA, 2010: 2959– 2964. [11] CALINON S, BILLARD A. Incremental learning of ges￾tures by imitation in a humanoid robot[C]//Proceedings of the ACM/IEEE international conference on Human-robot interaction. Arlington, VA, USA, 2007: 255–262. [12] HERSCH M, GUENTER F, CALINON S, et al. Dynam￾ical system modulation for robot learning via kinesthetic demonstrations[J]. IEEE transactions on robotics, 2008, 24(6): 1463–1467. [13] SCHAAL S, ATKESON C, VIJAYAKUMAR S. Scal￾able locally weighted statistical techniques for real time robot learning[J]. Applied intelligence-special issue on scalable robotic applications of neural networks, 2002, 17(1): 49–60. [14] PETERNEL L, OZTOP E, BABIČ J. A shared control method for online human-in-the-loop robot learning based [15] on locally weighted regression[C]//Proceedings of 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems. Daejeon, South Korea, 2016: 3900–3906. MCCORMICK J, VINCS K, NAHAVANDI S, et al. Teaching a digital performing agent: Artificial neural net￾work and hidden markov model for recognising and per￾forming dance movement[C]//Proceedings of the 2014 In￾ternational Workshop on Movement and Computing. Par￾is, France, 2014: 70. [16] 于建均, 吴鹏申, 左国玉, 等. 基于 RNN 的机械臂任务 模仿系统 [J]. 北京工业大学学报, 2018, 44(11): 1401– 1408. YU Jianjun, WU Pengshen, ZUO Guoyu, et al. Robot arm task imitation system based on RNN[J]. Journal of Beijing University of Technology, 2018, 44(11): 1401–1408. [17] 于建均, 门玉森, 阮晓钢, 等. 在书写任务中的基于轨迹 匹配的模仿学习 [J]. 北京工业大学学报, 2016, 42(8): 1144–1152. YU Jianjun, MEN Yusen, RUAN Xiaogang, et al. Imita￾tion learning based on trajectory matching in the writing task[J]. Journal of Beijing University of Technology, 2016, 42(8): 1144–1152. [18] IJSPEERT A J, NAKANISHI J, HOFFMANN H, et al. Dynamical movement primitives: learning attractor mod￾els for motor behaviors[J]. Neural computation, 2013, 25(2): 328–373. [19] PARASCHOS A, RUECKERT E, PETERS J, et al. Mod￾el-free probabilistic movement primitives for physical in￾teraction[C]//Proceedings of 2015 IEEE/RSJ Internation￾al Conference on Intelligent Robots and Systems. Ham￾burg, Germany, 2015: 2860–2866. [20] KOCH K H, CLEVER D, MOMBAUR K, et al. Learn￾ing movement primitives from optimal and dynamically feasible trajectories for humanoid walking[C]//Proceed￾ings of 2015 IEEE-RAS 15th International Conference on Humanoid Robots. Seoul, South Korea, 2015: 866–873. [21] KOBER J, GIENGER M, STEIL J J. Learning movement primitives for force interaction tasks[C]//Proceedings of 2015 IEEE International Conference on Robotics and Automation. Seattle, USA, 2015: 3192–3199. [22] WIGGINS S. Introduction to applied nonlinear dynamic￾al systems and chaos[M]. 2nd ed. New York: Springer Science & Business Media, 2003. [23] SEEGER M. Gaussian processes for machine learning[J]. International journal of neural systems, 2004, 14(2): 69–106. [24] [25] KHANSARI-ZADEH S M, BILLARD A. BM: an iterat- 第 5 期 于建均，等：基于动态系统的机器人模仿学习方法研究 ·1033·