In this paper we propose a methodology for the statistical generalization of the available sensorimotor knowledge in real-time. Example trajectories are generalized by applying Gaussian process regression, using the parameters describing a task as query points into the trajectory database. We show on real-world tasks that the proposed methodology can be integrated into a sensory feedback loop, where the generalization algorithm is applied in real-time to adapt robot motion to the perceived changes of the external world.
COBISS.SI-ID: 25861415
This paper describes a methodology that enables the generalization of the available sensorimotor knowledge. New actions are synthesized by the application of statistical methods, where the goal and other characteristics of an action are utilized as queries to create a suitable control policy, taking into account the current state of the world. The proposed approach enables the generation of a wide range of policies without requiring an expert to modify the underlying representations to account for different task-specific features and perceptual feedback. The paper also demonstrates that the proposed methodology can be integrated with an active vision system of a humanoid robot. While 3D vision on humanoid robots with complex oculomotor systems is often difficult due to the modeling uncertainties, we show that these uncertainties can be accounted for by the proposed approach.
COBISS.SI-ID: 23918375
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
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