RoboLeader: An Intelligent Agent for Enhancing Supervisory Control of Multiple Robots

Report No. ARL-TR-5239
Authors: Jessie Y. C. Chen, Michael J. Barnes, Zhihua Qu*, and Mark G. Snyder*
Date/Pages: July 2010; 42 pages
Abstract: We developed an intelligent agent, RoboLeader, that could assist human operators in controlling a team of robots. More specifically, RoboLeader was able to help the operators with their route planning tasks. Although there were no significant differences between the RoboLeader and Baseline conditions for target detection performance, participants in the RoboLeader group reduced their mission completion times by ~13% compared to Baseline. We also compared the operators' target detection performance in the four-robot and eight-robot conditions. The results showed that the participants detected significantly fewer targets when there were eight robots present, compared to the four-robot condition; participants with higher spatial ability, however, detected more targets than did those with lower spatial ability. Participants also experienced significantly higher workload with eight robots, and those with better attentional control reported lower workload than did those with poorer attentional control. Females also reported significantly higher workload than did males.
Distribution: Approved for public release
  Download Report ( 1.531 MBytes )
If you are visually impaired or need a physical copy of this report, please visit and contact DTIC.
 

Last Update / Reviewed: July 1, 2010