Non-parametric Gaussian process movement primitive with via-point constraint for effective and safe robot skill learning

Abstract

Learning from demonstration (LFD) algorithms has been proven to be an effective way to encode basic human skills, such as probabilistic movement primitives (ProMPs). However, such algorithms are based on parametric methods, which means that more effort is required to expand to multi-dimensional and high reproduction accuracy. In this article, a novel non-parametric LFD algorithm is proposed, named Gaussian process movement primitive based on Gaussian mixture regression (GPGR), which has lower computational complexity and high accuracy. We encapsulate the variability of the demonstration set into the prior of Gaussian processes and propose a necessary and sufficient condition to ensure that the generated trajectory can pass the expected via point with 100% probability, which is different from existing ProMPs and their variants. In addition, we propose a novel trajectory obstacle avoidance method. The method allows efficient and safe robot obstacle avoidance by solving for a small number of via points. The effectiveness of the algorithm is validated through a series of experiments on the LASA dataset and the Franka Emika Panda robot.