Autonomous human-robot proxemics: A robot-centered approach

Abstract

Our approach enables the robot to execute proxemic behaviors that improve speech and gesture recognition for both the robot and the human, even in noisy and cluttered environments. This work has been deployed on two different mobile robot platforms: (1) the PR2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , and (2) the Bandit <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> upper body humanoid atop an iRobot Ava <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> mobile base. This demonstrates the portability of the approach.