Recognizing and Interpreting Gestures on a Mobile Robot

Gesture recognition is an important skill for robots that work closely with humans Gestures help to clar ify spoken commands and are a compact means of re laying geometric information We have developed a real time three dimensional gesture recognition sys tem that resides on board a mobile robot Using a coarse three dimensional model of a human to guide stereo measurements of body parts the system is ca pable of recognizing six distinct gestures made by an unadorned human in an unaltered environment An active vision approach focuses the vision system s at tention on small moving areas of space to allow for frame rate processing even when the person and or the robot are moving This paper describes the gesture recognition system including the coarse model and the active vision approach This paper also describes how the gesture recognition system is integrated with an intelligent control architecture to allow for complex gesture interpretation and complex robot action Re sults from experiments with an actual mobile robot are given