General-purpose autonomous robots must have the ability to combine the available sensorimotor knowledge in order to solve more complex tasks. In this paper, we investigated the problem of sequencing of dynamic movement primitives. We proposed two new methodologies which both ensure that consecutive movement primitives are joined together in a continuous way (up to second-order derivatives).
COBISS.SI-ID: 25192487
When describing robot motion with dynamic movement primitives (DMPs), goal (trajectory endpoint), shape, and temporal scaling parameters are used. In reinforcement learning with DMPs, usually goals and temporal scaling parameters are predefined and only the weights for shaping a DMP are learned. Many tasks, however, exist where the best goal position is not a priori known, requiring to learn it. In this paper we specifically addressed the question of how to simultaneously combine goal and shape parameter learning.
COBISS.SI-ID: 25079079