The application of robots in contact with humans, in services or assistance, implies the realization of effective and acceptable human-robot interaction. In humans, vision plays a significant role in social interaction, like for example in the recognition of faces and expressions, as well as in gesture understanding. Visuo-motor coordination of eye and neck movements in humans presents high performances in terms of accuracy, speed, effectiveness. This is due to the mechanical, cinematic, and dynamic features of the head muscular-skeletal apparatus and to the peculiar processing of visual data, detected with a space variant resolution. The work presented in this paper aims at employing retina-like cameras on a human-like robotic head, reproducing similar degrees of freedom, ranges of motion, speeds, and accelerations of human neck and eye movements, in order to improve visuo-motor coordination. The use of retina-like cameras allows a faster human-like processing of visual information, better suited for the control of head movements. On the other hand, retina-like cameras provide high resolution information only in a small area of the image and thus need to be dynamically focused on the points of interest. Experimental trials were focused on the capability of identifying and tracking human faces, as a first step of human-robot interaction. Preliminary experimental results show the feasibility of a smooth face tracking, by a closed control loop for the head movements, based on retina-like vision.
|ジャーナル||Proceedings - IEEE International Conference on Robotics and Automation|
|出版ステータス||Published - 2003 12 9|
|イベント||2003 IEEE International Conference on Robotics and Automation - Taipei, Taiwan, Province of China|
継続期間: 2003 9 14 → 2003 9 19
ASJC Scopus subject areas