A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills

Alexander Fabisch

In: Advances in Robot Design and Intelligent Control - Proceedings of the 28th Conference on Robotics in Alpe-Adria-Danube Region. International Conference on Robotics in Alpe-Adria-Danube Region (RAAD-2019) June 19-21 Kaiserslautern Germany Advances in Intelligent Systems and Computing (AISC) Springer 2019.


Imitation learning is a way to teach robots skills that are demonstrated by humans. Transfering skills between these different kinematic structures seems to be straightforward in Cartesian space. Because of the correspondence problem, however, the result will most likely not be identical. This is why refinement is required, for example, by policy search. Policy search in Cartesian space is prone to reachability problems when using conventional inverse kinematic solvers. We propose a configurable approximate inverse kinematic solver and show that it can accelerate the refinement process considerably. We also compare empirically refinement in Cartesian space and refinement in joint space.

Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence