Selecting and Commanding Individual Robots in a Vision-Based Multi-Robot System
This video presents a computer vision based system for interaction between a single human and multiple robots. Face contact and motion-based gestures are used as two different non-verbal communication channels; a user first selects a particular robot by simply looking at it, then assigns it a task by waving his or her hand.
Research by Alex Couture-Beil, Richard T. Vaughan, and Greg Mori of the, Autonomy Lab and Vision & Media Lab at Simon Fraser University, Burnaby, B.C., Canada
This video also appears in the video track of HRI'10.
I just wish I will not find one of those looking at me while I sleep... creepy! =D
Enough with the silliness, good Job Alex, and good luck for your defense ;)
itallia1 2 years ago
Nice use of robot attention states in this project. I wanted to do something similar for my robot project where I wanted the robot to ignore voice commands if the user wasnt facing the robot (a high face recognition score). Also I wanted to try a similar gesture recognition to tell the robot to be silent if it started talking and I wanted to stop it. E.g. holding a hand with a raised index finger. Its a rather fun challenge to find a natural way of interaction with robot systems.
64jcl 2 years ago