Using cognitive models to design dynamic task allocation systems

Many operations in Intelligence, Surveillance, and Reconnaissance (ISR) involve balancing multiple simultaneous interdependent tasks and coordinating between multiple teammates. Recently, autonomous managers (AMs) were proposed as a method for optimizing performance in team-based workflows using dynamic reallocation in response to changes in workload and performance. We demonstrate how cognitive models can be used in the design and evaluation of AMs. Specifically, cognitive models can be used to inform an AM’s decision policy, and to stress test an AM under a wide variety of conditions. Simulation 1 tested the robustness of numerous AMs across a wide range of cognitive agents. We found that a simpler cognitive model in the AM’s decision system was more robust than more complex models. In the second simulation study, we compared dynamic task reallocation and corrective feedback to improve performance of cognitive agents based on the ACT-R cognitive architecture. Our results indicate that both interventions have the potential to improve performance, and that the most robust AM from simulation 1 can improve the performance of a model with realistic learning dynamics. Our simulations demonstrate that cognitive models are useful for designing and evaluating AMs for multiple military applications, including ISR.