Sigma as an Augmented Cognitive Architecture for Human Exploration Missions Beyond Cislunar Orbit

Deep space exploration missions involving humans present many obstacles that must be overcome in order to provide the crew with the necessary resources and abilities to make the mission successful. Along with the many concerns surrounding astronaut health and safety during long duration space flight is the ability for astronauts to work autonomously with limited assistance from mission control. In an effort to resolve the critical problem of communication delays to and from Earth and provide the crew with the support they need to carry out their mission, nFlux proposes an autonomous cognitive agent built from the capabilities of Sigma to assist astronauts during deep space missions. Sigma is a cognitive architecture and an integrated computational model of intelligence that combines four decades of research in cognitive architectures, probabilistic graphical models and deep learning that can be used to build autonomous intelligent agents. In particular, Sigma leverages factor graphs towards a uniform grand unification of not only traditional cognitive capabilities but also critical non-cognitive aspects, creating unique opportunities for the construction of new kinds of cognitive models that possess a Theory of Mind and are perceptual, autonomous, interactive, affective, and adaptive. Sigmarsquo;s graphical architecture has recently been extended to handle neural networks. Sigma has quite general parameter learning capabilities, in that probabilistic, neural, and reinforcement learning capabilities all emerge from a local gradient-descent-based learning mechanism operating at the code of the architecture. The aspiration for uniform grand unification, plus this unique blend of capabilities, make Sigma a well-equipped candidate to tackle the challenge of intelligent agents for deep space exploration.