A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills
In Advances in Robot Design and Intelligent Control - Proceedings of the 28th Conference on Robotics in Alpe-Adria-Danube Region, (RAAD-2019), 19.6.-21.6.2019, Kaiserslautern, Springer, series Advances in Intelligent Systems and Computing, 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.
learning from demonstration, imitation learning, reinforcement learning, policy search, inverse kinematics