Probabilistic Movement Primitives

Abstract

Abstract—Movement primitives are a promising approach for modular and re-usable movement generation, and suitable for data-driven movement acquisition. Beneficial properties such as simultaneous activation of multiple primitives, optimal movement encoding for stochastic systems, and generalization to new targets, are absent in most common approaches. We propose a probabilistic approach for generating, learning, and re-using movement primitives that overcomes these limitations. We represent a movement primitive as a probability distribution over trajectories. As a consequence, we can activate primitives simultaneously, smoothly blend together, generalize to new target states and encode optimal trajectories in stochastic systems. We compare our approach to the existing state-of-the art and present real robot results for learning from demonstration. Movement primitives (MP) are considered to be a state