Title :
Learning and evaluation of a vergence control system inspired by Hering´s law
Author :
Mutti, Flavio ; Alessandro, Cristiano ; Angioletti, Marco ; Bianchi, Andrea ; Gini, Giuseppina
Author_Institution :
DEI, Politec. di Milano, Milan, Italy
Abstract :
We develop a bio-inspired controller for an active stereo vision system based on the Hering´s law. We extend a model already proposed in literature in two ways. Firstly we evaluate the performance of the controller, inspecting its capability to foveate a generic feature in the 3D space, and the robustness respect to the initial angular configuration of the stereo system. Secondly we introduce the redundant component of the neck. Using a classical learning method we tune the controller to adapt to the controlled system. We investigate how the redundancy is solved by the learned controller, and show that the performance increases and the controlled stereo system generates human-like trajectories.
Keywords :
learning (artificial intelligence); mobile robots; robot vision; stereo image processing; trajectory control; 3D space; Hering law; active stereo vision system; bio-inspired controller; classical learning method; controlled stereo system; human-like trajectories; initial angular configuration; redundant component; vergence control system; Aerospace electronics; Biological system modeling; Cameras; Control systems; Mathematical model; Neck; Testing;
Conference_Titel :
Biomedical Robotics and Biomechatronics (BioRob), 2012 4th IEEE RAS & EMBS International Conference on
Conference_Location :
Rome
Print_ISBN :
978-1-4577-1199-2
DOI :
10.1109/BioRob.2012.6290920