Efficient people search and gesture recognition using a Kinect interfaced mobile robot

This paper describes the programming and application of human searching and gesture recognition using a neck-like swivel mechanism attached to a mobile robot Pioneer 3-DX interfaced with a Microsoft Kinect sensor. We utilize color, depth and skeleton data streams from the Kinect to find and track people for gesture commands to do basic robotic movements like wander around, follow-me etc. Our findings from experimental evaluation of the developed system suggest that mounting of the Kinect on a neck-like mechanism helps the robot efficiently search for a person and reduce the total accumulated error in its odometry compared to having the sensor fixed to the robot base. Overall, the developed platform is very robust and flexible in terms of expandability.