Recognizing hand posture by vision: applications in humanoid personal robotics

Abstract

In the development of humanoid personal robots, accompanying the life of humans in their everyday activities, vision is no doubt an extremely important sensory capability to provide the robots with. We propose the application of robot vision to the identification of hand posture, as a first step in gesture detection, for two main classes of reasons: 1) the recognition of human hand posture can help human-robot interaction, especially in relation to 'teaching by demonstration'; 2) the recognition of the robot hand can allow visual servoing, especially helpful in environments and tasks with a high level of uncertainty. The paper presents the development of a vision system for hand posture recognition, by describing the basic algorithmic implementation, based on symbolic representations, and reporting the experimental results obtained in the recognition of a three-fingered robotic hand.