Robot Learning by Demonstration with local Gaussian process regression
作者： M Schneider , W Ertel
DOI: 10.1109/IROS.2010.5650949
关键词: Robotic arm 、 Task (project management) 、 Robot 、 Human–robot interaction 、 Artificial intelligence 、 Robot learning 、 Data modeling 、 Machine learning 、 Gaussian process 、 Engineering 、 Trajectory
摘要: In recent years there was a tremendous progress in robotic systems, and however also increased expectations: A robot should be easy to program reliable task execution. Learning from Demonstration (LfD) offers very promising alternative classical engineering approaches. LfD is natural way for humans interact with robots will an essential part of future service robots. this work we first review heteroscedastic Gaussian processes show how these can used encode task. We then introduce new process regression model that clusters the input space into smaller subsets similar [11]. next step approaches fit by framework [2], [3]. At end present experiment on real arm shows all interact.
hs-weingarten.de 参考文章(19)
Stefan Schaal, Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics Adaptive Motion of Animals and Machines. pp. 261- 280 ,(2006) , 10.1007/4-431-31381-8_23
Carl Edward Rasmussen, Joaquin Quiñonero-Candela, A Unifying View of Sparse Approximate Gaussian Process Regression Journal of Machine Learning Research. ,vol. 6, pp. 1939- 1959 ,(2005) , 10.5555/1046920.1194909
Edward Snelson, Zoubin Ghahramani, None, Local and global sparse Gaussian process approximations. international conference on artificial intelligence and statistics. pp. 524- 531 ,(2007)
Christopher K I Williams, Carl Edward Rasmussen, Gaussian Processes for Machine Learning ,(2005)
Brenna D. Argall, Sonia Chernova, Manuela Veloso, Brett Browning, A survey of robot learning from demonstration Robotics and Autonomous Systems. ,vol. 57, pp. 469- 483 ,(2009) , 10.1016/J.ROBOT.2008.10.024
Carl Rasmussen, Zoubin Ghahramani, None, Infinite Mixtures of Gaussian Process Experts neural information processing systems. ,vol. 14, pp. 881- 888 ,(2001)
Zoubin Ghahramani, Edward Snelson, Sparse Gaussian Processes using Pseudo-inputs neural information processing systems. ,vol. 18, pp. 1257- 1264 ,(2005)
Duy Nguyen-Tuong, J. Peters, Local Gaussian process regression for real-time model-based robot control intelligent robots and systems. pp. 380- 385 ,(2008) , 10.1109/IROS.2008.4650850
D. Grimes, R. Chalodhorn, R. Rao, Dynamic Imitation in a Humanoid Robot through Nonparametric Probabilistic Inference robotics science and systems. ,vol. 02, ,(2006) , 10.15607/RSS.2006.II.026
Daniel H Grollman, Odest Chadwicke Jenkins, Dogged Learning for Robots international conference on robotics and automation. pp. 2483- 2488 ,(2007) , 10.1109/ROBOT.2007.363692