Developing Mixed-Initiative Interaction with Intelligent Systems: Lessons Learned from Supervising Multiple UAVs

Hanson, Mark L.; Roth, Emilie M.; Hopkins, Chris; Mancuso, Vince

doi:10.2514/6.2004-6310

Cited by 5 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hanson et al found that human operators paired with an algorithm for scheduling multiple UAVs desired a greater understanding of why the algorithm made certain recommendations [45]. They also observed that operators tended to think less in terms of numerical optimization when planning UAV routes but more in abstract terms about the overall goals or tactical objectives that they wanted to accomplish.…”

Section: Introductionmentioning

confidence: 99%

“…In these previous studies, the assumption was that the planning algorithms were static and unchanging throughout the period in which the human interacted with the automation. Operator SA was typically low, and operators complained about the lack of transparency in how the automation generated plans [12,18,33,45]. Thus, developing a method for human operators to modify the objective function of the automated planner in real time could provide the transparency necessary to maintain operator SA, while enabling operators to communicate their desires to the automation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Operator Object Function Guidance for a Real-Time Unmanned Vehicle Scheduling Algorithm

Clare

Cummings

How

et al. 2012

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

Advances in autonomy have made it possible to invert the typical operator-to-unmanned-vehicle ratio so that a single operator can now control multiple heterogeneous unmanned vehicles. Algorithms used in unmanned-vehicle path planning and task allocation typically have an objective function that only takes into account variables initially identified by designers with set weightings. This can make the algorithm seemingly opaque to an operator and brittle under changing mission priorities. To address these issues, it is proposed that allowing operators to dynamically modify objective function weightings of an automated planner during a mission can have performance benefits. A multiple-unmanned-vehicle simulation test bed was modified so that operators could either choose one variable or choose any combination of equally weighted variables for the automated planner to use in evaluating mission plans. Results from a human-participant experiment showed that operators rated their performance and confidence highest when using the dynamic objective function with multiple objectives. Allowing operators to adjust multiple objectives resulted in enhanced situational awareness, increased spare mental capacity, fewer interventions to modify the objective function, and no significant differences in mission performance. Adding this form of flexibility and transparency to automation in future unmanned vehicle systems could improve performance, engender operator trust, and reduce errors.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Operator Object Function Guidance for a Real-Time Unmanned Vehicle Scheduling Algorithm

Clare

Cummings

How

et al. 2012

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

show abstract

“…Several recent research efforts (e.g., Hanson, Roth, Hopkins, & Mancuso, 2004;Lewis, Wang, & Scerri, 2006) have focused on designing interface concepts and technologies to allow a single operator to manage multiple unmanned vehicles (UVs) and increase operator span of control (i.e., the number of vehicles a single operator can control). The situation changes significantly, however, when additional UV assets of various types are introduced.…”

Section: Introductionmentioning

confidence: 99%

Applying SA-Oriented Design to the Integrative Collaborative Control of Multiple Unmanned Vehicle Systems

Connors

Strater

Riley

et al. 2008

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

The cognitive processes underlying collaboration and knowledge interoperability are challenged in team-based multi-vehicle supervisory control beyond those typically found in solitary unmanned vehicle (UV) control. This paper addresses the application of SA-Oriented Design principles to the development of collaborative control interfaces that enable small co-located or distributed teams of operators to plan and manage multiple UVs while supporting high levels of situation awareness (SA) while improving knowledge construction and collaborative teamwork. Following this approach, Goal Directed Task Analyses for three separate unmanned systems were combined with a novel concept of operations for the Littoral Combat Ship (LCS) platform and the results of subject matter expert role-playing to rapidly prototype the collaborative control interface environment.

show abstract

Aircraft Autonomy

Miotto¹,

Singh²,

Paduano³

et al. 2015

Advances in Control System Technology for Aerospace Applications

View full text Add to dashboard Cite

Developing Mixed-Initiative Interaction with Intelligent Systems: Lessons Learned from Supervising Multiple UAVs

Cited by 5 publications

References 3 publications

Operator Object Function Guidance for a Real-Time Unmanned Vehicle Scheduling Algorithm

Operator Object Function Guidance for a Real-Time Unmanned Vehicle Scheduling Algorithm

Applying SA-Oriented Design to the Integrative Collaborative Control of Multiple Unmanned Vehicle Systems

Aircraft Autonomy

Contact Info

Product

Resources

About