Assisting Interruption Recovery in Supervisory Control of Multiple Uavs

Abstract

Performance degradation due to interruptions is a critical issue, particularly when people are supervising highly autonomous systems in time and safety critical environments. Previous research in the development of automated support to help supervisory control operators resume task activities after an interruption has had limited success. This paper describes two new interruption recovery approaches that attempt to mitigate the disadvantages of previous approaches. In particular, this paper describes the design and initial investigation of a prototype assistive interface developed to support interruption recovery for supervisory control of multiple unmanned aerial vehicles (UAVs). These two 'replay'-type interruption recovery approaches enable increased user-control of the event discovery process and provide event 'bookmarks' to highlight emergent system events. The findings from this initial study provide several recommendations for the future design of interruption assistance tools for human supervisory control tasks.

Background Sound Impairs Interruption Recovery in Dynamic Task Situations: Procedural Conflict?

“…If auditory distraction hinders the reacquisition of SA following interruption, external aids that highlight important changes in the task environment may help focus attention and facilitate the recovery process. Examples include an instant replay device (Scott, Mercier, Cummings, & Wang, ) and the Change History EXplicit (Smallman & St. John, ; St. John, Smallman, & Manes, ; but see Vallières, Vachon, & Tremblay, ), which logs all key changes in an easily accessible table. However, a problem with many support tools is that although one aspect of cognition may be augmented (e.g., change detection), another aspect may be impaired (e.g., speed of response; see, e.g., Vachon, Lafond, Vallières, Rousseau, & Tremblay, ).…”

Human-Agent Teaming for Multi-Robot Control: A Literature Review

“…When controlling multiple robots at the same time, it is inevitable that the operator will focus on some aspects of the environment (e.g., one of the robots) before resuming his/her monitoring of all the robots. Techniques that facilitate task resumption have been proposed and tested in various tasking environments (Ratwani et al, 2007;Scott et al, 2006;St. John et al, 2005).…”

“…John et al, 2005). Some techniques focus on reminding the operator where they were before the interruption (Ratwani et al, 2007), while others present aids for the operator to quickly review what happened during the interruption (Scott et al, 2006;St. John et al, 2005).…”

“…Other researchers have proposed replay tools that can communicate to the operators recent significant events via video. For example, Scott et al, (2006) presented two types of replay tools, one replaying the events at a 10× real time speed and the other presenting bookmarks on the event timelines so the operator could view the replay by selecting the bookmarks. Results showed that both replay techniques were effective, especially when the tasking environment was challenging.…”

“…Provide visual summary of critical events but limit the summary only to goal-related events 3. Clearly indicate relationships between past and current system state (Scott et al, 2006;p. 703) Dorneich et al, (2012) took a different approach and developed a wearable adaptive system, the Communications Scheduler, which used physiological sensors (EEG and electrocardiogram) to detect operators' cognitive workload in a multitasking situation (including navigation, cognitive, monitoring, and maintaining SA).…”