TY - JOUR T1 - Pose Estimation Through Cue Integration: A Neuroscience-Inspired Approach JF - Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on Y1 - 2012 A1 - Eris Chinellato A1 - Beata J. Grzyb A1 - Angel P. del Pobil KW - binocular cue integration KW - Biological system modeling KW - Cameras KW - Computational modeling KW - Computer Simulation KW - Computer-Assisted KW - Cybernetics KW - Depth Perception KW - Estimation KW - Grasping KW - grippers KW - Humans KW - Image Processing KW - Intelligent robots KW - Models KW - monocular cue integration KW - Neurological KW - neuropsychological effects KW - neuroscience-inspired model KW - object estimation KW - perspective orientation estimator KW - pose estimation KW - Reliability KW - Reproducibility of Results KW - robot sensory systems KW - robot vision KW - robot vision systems KW - Robotics KW - Robots KW - stereo image processing KW - stereo vision KW - stereoptic orientation estimator KW - Task Performance and Analysis KW - visual estimation KW - visual perception KW - Visualization AB -

The aim of this paper is to improve the skills of robotic systems in their interaction with nearby objects. The basic idea is to enhance visual estimation of objects in the world through the merging of different visual estimators of the same stimuli. A neuroscience-inspired model of stereoptic and perspective orientation estimators, merged according to different criteria, is implemented on a robotic setup and tested in different conditions. Experimental results suggest that the integration of multiple monocular and binocular cues can make robot sensory systems more reliable and versatile. The same results, compared with simulations and data from human studies, show that the model is able to reproduce some well-recognized neuropsychological effects.

VL - 42 ER -