Force Control and Reaching Movements on the iCub Humanoid Robot

详细信息    查看全文

• 刊名：Springer Tracts in Advanced Robotics
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：100
• 期：1
• 页码：161-182
• 全文大小：785 KB
• 参考文献：1.G. Metta, L. Natale, F. Nori et al., The iCub humanoid robot: an open-systems platform for research in cognitive development. Neural Networks, special issue on Social Cognition: From Babies to Robots. 23, 1125–1134 (2010)
  2.L. Villani, J. De Shutteer, Force control—Chapter 7, eds. by B. Siciliano, O. Khatib. Springer Handbook of Robotics (Springer, 2008)
  3.L. Sciavicco, B. Siciliano, Modelling and Control of Robot Manipulators. Advance textbooks in Control and Signal Processing, 2nd edn. (Springer, 2005)
  4.G. Metta The iCub website (2010). http://​www.​iCub.​org
  5.G. Metta, D. Vernon, G. Sandini, The RobotCub approach to the development of cognition: implications of emergent systems for a common research agenda in epigenetic robotics. in 5th Epigenetic Robotics Workshop, Nara, Japan, July 2005
  6.A.R. Tilley, The Measure of Man and Woman: Human Factors in Design (Wiley Interscience, 2002)
  7.N.G. Tsagarakis, G. Metta, G. Sandini et al., iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research. Adv. Robot. 21(10), 1151–1175 (2007)CrossRef
  8.P. Fitzpatrick, G. Metta, L. Natale, Towards long-lived robot genes. Robot. Auton. Syst. 56(1), 29–45 (2008)CrossRef
  9.R. Featherstone, D.E. Orin, Dynamics—Chapter 2, in B. Siciliano, O. Khatib, Springer Handbook of Robotics (Springer, 2008)
  10.A. Gijsberts, G. Metta, Incremental learning of robot dynamics using random features. in IEEE International Conference on Robotics and Automation. Shanghai, China, 9–13 May 2011
  11.D. Nguyen-Tuong, J. Peters, M. Seeger, Computed torque control with nonparametric regression models. in American Control Conference (ACC 2008), pp. 212–217, June 2008
  12.A. Rahimi, B. Recht, Random features for large-scale kernel machines. Adv. Neural Inform. Process. Syst. 20, 1177–1184 (2008)
  13.A. Wätcher, L.T. Biegler, On the implementation of a primal-dual interior point filter line search algorithm for large-scale nonlinear programming. Math. Programm. 106(1), 25–57 (2006)
  14.M. Hersch, A.G. Billard, Reaching with multi-referential dynamical systems. Auton. Robots 25(1–2), 71–83 (2008)CrossRef
  15.W. Abend, E. Bizzi, P. Morasso, Human arm trajectory formation. Brain 105, 331–348 (1982)CrossRef
  16.U. Pattacini, F. Nori, L. Natale, G. Metta, G. Sandini, An experimental evaluation of a novel minimum-Jerk Cartesian controller for humanoid robots. in IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1668–1674, Taipei, Taiwan, 18–22 Oct 2010
  17.A.S. Deo, I.D. Walker, Robot subtask performance with singularity robustness using optimal damped least-squares. in IEEE International Conference on Robotics and Automation (1992)
  18.H.Y. Lee, B.J. Yi, Y. Choi (2007) A realistic joint limit algorithm for kinematically redundant manipulators. in IEEE International Conference on Control, Automation and Systems
  19.The Orocos website. http://​www.​orocos.​org/​kdl
  20.B.D. Lucas, T. Kanade, An iterative image registration technique with an application to stereo vision. in Proceedings of IJCAI, pp. 674–679 (1981)
  
• 作者单位：Giorgio Metta (5)
  Lorenzo Natale (5)
  Francesco Nori (5)
  Giulio Sandini (5)
  
  5. Robotics, Brain and Cognitive Sciences, Istituto Italiano di Tecnologia, Via Morego 30, Genoa, Italy
  
• 丛书名：Robotics Research
• ISBN：978-3-319-29363-9
• 刊物类别：Engineering
• 刊物主题：Automation and Robotics
  Control Engineering
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1610-742X
• 卷排序：100

文摘

This paper is about a layered controller for a complex humanoid robot: namely, the iCub. We exploited a combination of precomputed models and machine learning owing to the principle of balancing the design effort with the complexity of data collection for learning. A first layer uses the iCub sensors to implement impedance control, on top of which we plan trajectories to reach for visually identified targets while avoiding the most obvious joint limits or self collision of the robot arm and body. Modeling errors or misestimation of parameters are compensated by machine learning in order to obtain accurate pointing and reaching movements. Motion segmentation is the main visual cue employed by the robot.