Modular Affective Reasoning-based Versatile Introspective Architecture (MARVIN)

Robotic vehicles, unmanned systems, and critical command and control networks need to operate effectively in complex, dynamic, and adversarial environments. Currently, fielded systems are not up to the task as they are not able to dynamically modify their behavior to suit the changing environment and they can be immobilized by simple component failures. Future operations will not tolerate such brittleness, especially given the interconnectivity demanded by network-centric warfare. Future fielded systems throughout the military will need more dynamic processing capabilities. Self-Aware Computing attempts to resolve this problem through metacognitive approaches to generating dynamic capabilities based on research into human adaptation. However, these approaches tend to ignore the impact of human emotions in that adaptation. Emotions are evolutionarily proven mechanisms that enable humans to rapidly and broadly adapt to threats, rapidly adapt to new situations, and effectively communicate threats and problems to others. We propose to develop Modular Affective Reasoning-Based Versatile Introspective (MARVIN) components that enhance self-aware systems by exploiting ideas from human affect to (1) adapt quickly to time-critical situations, (2) adapt to new situations and carry learning over to new situations, and (3) interact with other networked systems in an efficient social manner.