A common characteristic of domains that require planning for allocation of scarce resources is the need to dynamically revise the plan as new requirements emerge and priorities change. We describe a prototype decision support system for planning and scheduling airlift that we developed for a military transport organization that enables agile plan adaptation as movement requirements, available airlift assets, and priorities change. The collaborative automated scheduler includes visualizations to foster improved situation awareness of available airlift assets versus total demand on those assets; mechanisms to enable users to communicate informal priorities and changes to those priorities; and mechanisms that enable users to explore alternative scheduling options in response to changes in movement requirements, priorities and available assets. A formal user evaluation study that included 12 participants representing three different organizational groups involved in transportation planning provided evidence that the prototype improves the ability to capture and communicate movement priorities, rapidly reallocate airlift assets to accommodate changes, and communicate/collaborate across organizational boundaries in managing airlift demand versus capacity.
We describe the most recent work-centered design for a military airlift organization. Earlier design cycles produced a set of coordinated visualizations to support synchronized air mission replanning. In this phase of the program automated planning support was incorporated to help C2 staff solve complex constraint problems across multiple missions and airfields. We describe our efforts at designing a replanning tool to work in collaboration with the human operator on complex replanning problems. A prototype was developed and used in an empirical evaluation comparing target user performance on complex constraint problems using either the visualizations alone or the visualizations with embedded automated support (collaborative planner). The collaborative planner significantly improved the speed and quality of dynamic replanning solutions. Post-test questionnaire ratings indicated users trusted the support provided by the automated aid. Design principles for effective collaborative automation are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.