Smart Information Flow Technologies - unmanned aerial vehicles

A Playbook™ for Real-time, Closed-Loop Control

admin — Wed, 29 Jul 2015 19:58:23 +0000

Keywords: delegation interfaces, tasking interfaces, unmanned air vehicles, robotics, hierarchical task networks, mixed initiative control, discrete event control

Abstract: SIFT has been developing an approach to adaptable automation control of multiple Unmanned Air Vehicles (UAVs) we call a PlaybookTM because it is based on the metaphor of a sports team’s book of acceptable plays. Playbook represents a “delegation” approach to human-automation interactions because it allows a human operator to task or delegate authority to automation with much of the same flexibility with which a human supervisor or team captain can delegate objectives, methods, constraints and even detailed instructions to subordinates. In previous work, we have described the Playbook architecture and approach, illustrated interfaces, presented initial data clarifying its benefits and describing collaborative interactions with it. Here, we review the Playbook concept and previous work and then report on newly implemented play capabilities including the ability for the Playbook to coordinate the activities of multiple UAVs to track a groundbased moving target—a play that requires Playbook to dynamically replan within authority delegated to it by the human operator.

Citation:

Funk, H., Goldman, R., Miller, C., Meisner, J., & Wu, P. (2005, March). A Playbook™ for Real-time, Closed-Loop Control. Submitted for inclusion in Proceedings of the 1st Annual Conference on Human-Robot Interaction. Salt Lake City, UT.

Date Published:

Tuesday, March 1, 2005

Publication File:

FGMMW-HRI05.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Optimizing to Satisfice: Using Optimization to Guide Users

admin — Wed, 29 Jul 2015 19:53:36 +0000

Keywords: playbook, unmanned aerial vehicle, delegation interfaces, overconstrained missions

Abstract: We describe a delegation-based solution to the planning overconstrainedUAV missions. SIFT’s PlaybookTM approach to UAV control allows single operators to request services from multiple-UAV teams, without excessive workload, specialized training, or platform-specific ground control systems. We use the metaphor of a sports team’s playbook: a user “calls a play” for a mission, relying on the system to flesh out the details. As in a sports playbook, the user has the freedom to add specifics at will. We have integrated Playbook with Geneva Aerospace’s VACS system ground station, to control multiple, heterogeneous, rotorcraft and fixed-wing UAVs. Using PVACS, we have discovered that overconstrained missions are particularly challenging, because it is difficult for operators find appropriate ways to relax constraints. To solve this problem we have added a “best-effort” planning mode to the Playbook. Best-effort plans may be directly useful, or can be used as a guideline in relaxing constraints.

Citation:

Goldman, R., Miller, C., Wu, P., Funk, H. & Meisner, J. (2005, January 18-20). Optimizing to Satisfice: Using Optimization to Guide Users. Proceedings of the American Helicopter Society’s International Specialists Meeting on Unmanned Aerial Vehicles. Chandler, AZ.

Date Published:

Tuesday, January 18, 2005

Publication File:

AHSismur05.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

The Playbook Approach to Adaptive Automation

admin — Wed, 29 Jul 2015 19:33:05 +0000

Keywords: playbook, supervisory control, unmanned aerial vehicle, play templates, adaptive automation, relaxed planning

Abstract: SIFT has pioneered a human-automation integration architecture, called PlaybookTM, based on a shared model of the tasks in the domain. This shared task model provides a means of human-automation communication about plans, goals, methods and resource usage—a process akin to referencing plays in a sports team’s playbook. The Playbook enables human operators to interact with subordinate systems with the same flexibility as with well-trained human subordinates, thus allowing for adaptive automation. We describe this approach and its application in an ongoing project called Playbook-enhanced Variable Autonomy Control SystemTM (P-VACS).

Citation:

Miller, C., Funk, H., Wu, P., Goldman, R., Meisner, J., & Chapman, M. The Playbook Approach to Adaptive Automation. Proceedings of the Human Factors and Ergonomics Society's 49th Annual Meeting, Orlando, FL.

Date Published:

Thursday, September 1, 2005

Publication File:

MFWGMC-HFES2005.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

A Playbook Approach to Variable Autonomy Control: Application for Control of Multiple, Heterogeneous Unmanned Air Vehicles

admin — Wed, 29 Jul 2015 18:50:55 +0000

Keywords: PVACS, VACS, unmanned aerial vehicles, overwatch

Abstract: As Unmanned Air Vehicles (UAVs) become more common, several core challenges emerge including the need for single operators to control, or perhaps more accurately, to request services from, multiple UAVs without the degree of workload, specialized training and platform-specific control interfaces which characteristize of current UAV operation. A challenging problem involves the dismounted, small unit soldier who may need services from a range of vehicles while in challenging situations such as urban combat. We are developing an approach to UAV control that addresses these challenges. We use the metaphor of a sports team’s playbook to enable both quick and complex, variable-initiative control of a variety of UAVs—the user of our Playbook “calls a play” which need not (but may, if the user desires) specify what type or how many UAVs should be used to satisfy it. We describe the Playbook-enhanced Variable Autonomy Control System (PVACS), which combines SIFT’s Playbook architecture and Geneva Aerospace’s Variable Autonomy Control System (VACS). We illustrate the capabilities and operations of PVACS in an extended walkthrough example involving a request for Overwatch—continued surveillance—of an urban intersection and the development and execution of a plan to satisfy that request using multiple, heterogeneous UAVs.

Citation:

Miller, C., Goldman, R., Funk, H., Wu, P. & Pate, B. (2004, June 7-10). A Playbook Approach to Variable Autonomy Control: Application for Control of Multiple, Heterogeneous Unmanned Air Vehicles. Paper presented in FORUM 60, the Annual Meeting of the American Helicopter Society, Baltimore, MD.

Date Published:

Monday, June 7, 2004

Publication File:

MGFWP-AHS04-fin.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages:

Tasking Interfaces: Associate Systems that know Who’s the Boss

admin — Tue, 28 Jul 2015 16:31:01 +0000

Keywords: UAV, shared task model, tasking intefaces

Abstract: Despite substantial technological success, “associate” systems continue to suffer from a fundamental, sociological problem— namely, that human operators of advanced automation are used to being in charge. We have recently begun adapting techniques from our associate research to the construction of “tasking” interfaces which enable the kind of interaction operators are used to having with intelligent, informed subordinates. Instead of being autonomous, or even truly mixedinitiative, “tasked” systems are always subordinate—but they know enough about the tasks in the domain that instructing them is vastly easier than instructing traditional automation systems. We use a shared task model to give advanced automation systems (e.g., Unmanned Air Vehicles—UAVs) the same task and goal understanding that the human has. When combined with a planner, the resulting system permits ‘tasking’ at all the various levels an intelligent subordinate should be able to accept: exhaustively specified plans to be performed exactly, partial plans which leave the planner free to create any full plan which includes those pieces, constraints which require the planner to stay away from certain methods or resources, or high-level goals for the automation to achieve however it thinks best. The net result is a human-machine system which is almost as capable as an associate, and which reduces human workload almost as much, yet which leaves the human more in control than an associate does.

Citation:

Miller, C., & Goldman, R. (1997, September 23-27). Tasking Interfaces: Associate Systems that know Who’s the Boss. Paper presented at the Proceedings of the 4th International Workshop on Human-Computer Teamwork, Krueth, Germany

Date Published:

Tuesday, September 23, 1997

Publication File:

AAAI-FS-01.pdf

Workflow: Editor Role:

Request Review

Workflow: Publisher Role:

Publish

Prevent Workflow Messages: