Learning of robot kinematic and dynamic models from data has attracted much interest recently as an alternative to manually defined models. However, the amount of data required to learn these models becomes large when the number of degrees of freedom increases and collecting it can be a timeintensive process. We employ transfer learning techniques in order to speed up learning of robot models, by using additional data obtained from other robots. We propose a method for approximating non-linear mappings between manifolds, which we call Local Procrustes Analysis (LPA), by adopting and extending the linear Procrustes Analysis method. Experimental results indicate that the proposed method offers an accurate transfer of data and significantly improves learning of the forward kinematics model. Furthermore, it allows learning a global mapping between two robots that can be used to successfully transfer trajectories.
Reference:
Makondo, N, Rosman, B.S. and Hasegawa, O. 2015. Knowledge transfer for learning robot models via local procrustes analysis. In: IEEE-RAS International Conference on Humanoid Robots, Seoul, Korea, November 3-5, 2015
Makondo, N., Rosman, B. S., & Hasegawa, O. (2015). Knowledge transfer for learning robot models via local procrustes analysis. http://hdl.handle.net/10204/8314
Makondo, N, Benjamin S Rosman, and O Hasegawa. "Knowledge transfer for learning robot models via local procrustes analysis." (2015): http://hdl.handle.net/10204/8314
Makondo N, Rosman BS, Hasegawa O, Knowledge transfer for learning robot models via local procrustes analysis; 2015. http://hdl.handle.net/10204/8314 .