System for Group Learning and Optimization of Collaborative Workflows (GLOW)

The Navy must train and deploy effective teams in a variety of complex domains, from intelligence analysis to field medicine. For example, intelligence analysts preparing the battlespace need a team of experts to interpret a variety of multi-INT sources and incorporate local socio-cultural context, and field medicine often requires a team of doctors skilled in a variety of disciplines. Training individual personnel in all the skills and knowledge required by these missions would be cost-prohibitive and inefficient. Instead, teams are constructed to optimize their collective expertise. To construct these teams, the Navy needs a team development system that manages task and learning assignments to dynamically construct teams with the expertise to achieve evolving mission objectives. To meet this need, we propose to design and demonstrate a system for Group Learning and Optimization of Collaborative Workflows (GLOW). GLOW constructs teams that have the collective expertise required to address complex mission tasks through a combination of dynamic task and personnel ecosystem models, task and learning assignment optimization, and tools for effective team communication and collaboration. Probabilistic predictive models evaluate potential contributors, and a simulated market algorithm distributes tasks and learning assignments to balance personal development and mission requirements.