Attaining Situational Awareness for Sliding Autonomy - Robotics Institute Carnegie Mellon University

Attaining Situational Awareness for Sliding Autonomy

Conference Paper, Proceedings of 1st ACM SIGCHI/SIGART Conference on Human-Robot Interaction (HRI '06), pp. 80 - 87, March, 2006

Abstract

We are interested in the problems of a human operator who is responsible for rapidly and accurately responding to requests for help from an autonomous robotic construction team. A difficult aspect of this problem is gaining an awareness of the requesting robot? situation quickly enough to avoid slowing the whole team down. One approach to speeding the initial acquisition of situational awareness is to maintain a buffer of data, and play it back for the human when their help is needed. We report here on an experiment to determine how the composition and length of this buffer affect the human? speed and accuracy in our multi-robot construction domain. The experiments show that, for our scenario, 5 - 10 seconds of one raw video feed led to the fastest operator attainment of situational awareness, while accuracy was maximized by viewing 10 seconds of three video feeds. These results are necessarily specific to our scenario, but we feel that they indicate general trends which may be of use in other situations. We discuss the interacting effects of buffer composition and length on operator speed and accuracy, and draw several conclusions from this experiment which may generalize to other scenarios.

BibTeX

@conference{Sellner-2006-9417,
author = {Brennan Peter Sellner and Laura M. Hiatt and Reid Simmons and Sanjiv Singh},
title = {Attaining Situational Awareness for Sliding Autonomy},
booktitle = {Proceedings of 1st ACM SIGCHI/SIGART Conference on Human-Robot Interaction (HRI '06)},
year = {2006},
month = {March},
pages = {80 - 87},
}