Editing Facilitating Operator Interaction with Quality of Service-based Multirobot Surveillance Systems

Research Topics
Robotic systems are becoming more practical in military applications. In fact, unmanned aerial vehicles (UAVs) are being used for surveillance and reconnaissance missions. Using UAVs for surveying a region of interest can increase situational awareness and decrease human casualty by allowing the operator to view the video feeds from the UAVs. However, current systems utilize complex one (or multiple) operator/one robot interfaces. In addition, human-in-the-loop models create issues because human operators tend to intervene more frequently if they do not trust the system or their expectations of the autonomy are not met. As a result, excessive human intervention could negatively affect workload, situational awareness, and performance.

Examining the expectations of autonomy and human intervention in a multi-robot surveillance task
In this reserach, we examine several approaches for cooperative surveillance using two UAVs. Additionally, we elucidate the role of human expectations in a surveillance task using a novel single operator/multiple UAV user interface. From this study, we found that most operators found the interface to be easy to learn and use. Also, most operators found the manual approach to be the most intuitive. The operators found the target faster and with shorter distances traveled when using the manual approach. Further, the frequency of waypoint selections in the semi-autonomous approach indicated that the expectations of autonomy in systems needs further studying. For future work, we will incorporate more UAVs into the interface and design mechanisms that match human expectations.

Facilitating operator interaction with quality of surveillance multi-robot systems
This research is aimed at allowing a single operator to efficiently manage multiple UAVs and interact effectively with higher levels of autonomy. Studies validate the system and elucidate factors that affect operator trust. Results suggest that a human operator can team with robots and effectively interact with higher levels of autonomy using environmental cues while promoting trust, lowering workload, and increasing situational awareness.

Publications

  • S. Dawson, C. Crawford, E. Dillon, and M. Anderson, “Examining the expectations of autonomy and human intervention in a multi-robot surveillance task,” 50th ACM Southeast Conference, March 2012. Poster Abstract.

Funding
This work was supported in part by the following NSF grant: IIP 1026528.