Reference Type | Conference Proceedings |
Author(s) | Koert, D.; Maeda, G.; Neumann, G.; Peters, J. |
Year | 2018 |
Title | Learning Coupled Forward-Inverse Models with Combined Prediction Errors |
Journal/Conference/Book Title | Proceedings of the International Conference on Robotics and Automation (ICRA) |
Keywords | 3rd-Hand,SKILLS4ROBOTS |
Abstract | Challenging tasks in unstructured environments require robots to learn complex models. Given a large amount of information, learning multiple simple models can offer an efficient alternative to a monolithic complex network. Training multiple models---that is, learning their parameters and their responsibilities---has been shown to be prohibitively hard as optimization is prone to local minima. To efficiently learn multiple models for different contexts, we thus develop a new algorithm based on expectation maximization (EM). In contrast to comparable concepts, this algorithm trains multiple modules of paired forward-inverse models by using the prediction errors of both forward and inverse models simultaneously. In particular, we show that our method yields a substantial improvement over only considering the errors of the forward models on tasks where the inverse space contains multiple solutions. |
Link to PDF | http://www.ausy.tu-darmstadt.de/uploads/Team/DorotheaKoert/cfim_final.pdf |