Multi-task Gaussian Process Learning of Robot Inverse Dynamics
Proc. Advances in Neural Information Processing Systems (NIPS '08)
dc.contributor.author | Chai, Kian Ming | |
dc.contributor.author | Klanke, Stefan | |
dc.contributor.author | Williams, Chris | |
dc.contributor.author | Vijayakumar, Sethu | |
dc.date.accessioned | 2010-08-23T12:26:22Z | |
dc.date.available | 2010-08-23T12:26:22Z | |
dc.date.issued | 2008 | |
dc.identifier.uri | http://hdl.handle.net/1842/3664 | |
dc.description.abstract | The inverse dynamics problem for a robotic manipulator is to compute the torques needed at the joints to drive it along a given trajectory; it is beneficial to be able to learn this function for adaptive control. A robotic manipulator will often need to be controlled while holding different loads in its end effector, giving rise to a multi-task learning problem. By placing independent Gaussian process priors over the latent functions of the inverse dynamics, we obtain a multi-task Gaussian process prior for handling multiple loads, where the inter-task similarity depends on the underlying inertial parameters. Experiments demonstrate that this multi-task formulation is effective in sharing information among the various loads, and generally improves performance over either learning only on single tasks or pooling the data over all tasks. | en |
dc.language.iso | en | en |
dc.subject | Informatics | en |
dc.title | Multi-task Gaussian Process Learning of Robot Inverse Dynamics | en |
dc.type | Conference Paper | en |
rps.title | Proc. Advances in Neural Information Processing Systems (NIPS '08) | en |
dc.extent.noOfPages | 8 | en |
dc.date.updated | 2010-08-23T12:26:23Z |