Title: Dynamic learning of action patterns for object acquisition

Authors: Gabriele Peters, Thomas Leopold

Addresses: Department of Computer Graphics, University of Dortmund, Otto-Hahn-Str. 16, D-44221 Dortmund, Germany. ' Department of Computer Graphics, University of Dortmund, Otto-Hahn-Str. 16, D-44221 Dortmund, Germany

Abstract: We propose an active vision system for the acquisition of internal object representations. The core of the approach is an agent which learns goal-directed action patterns depending on the perceived environment via reinforcement learning. The user supervision is restricted to the definition of this goal in the form of a reward function. We demonstrate this approach by means of learning a strategy to scan an object. The agent moves a virtual camera around an object and is able to adapt her scan path dynamically to different conditions of the environment such as different objects and different goals of the data acquisition. The purpose of the acquisition which we consider here is the view-based reconstruction of non-acquired views. The scan pattern obtained after the learned path has stabilised allows a better reconstruction of unfamiliar views than random scan paths.

Keywords: active vision; object acquisition; view reconstruction; object representations; reinforcement learning; automatic learning; action patterns; goal-directed behaviour; adaptive control; dynamic learning.

DOI: 10.1504/IJISTA.2007.012477

International Journal of Intelligent Systems Technologies and Applications, 2007 Vol.2 No.2/3, pp.113 - 124

Published online: 19 Feb 2007 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article