Autonomous Systems for Space Exploration

The exploration of space requires advanced technologies that will better enable both humans and robotic spacecraft to maintain a sustained lunar presence, support Mars exploration, operate in deep space, and explore other destinations in our solar system. Examples of such missions include robotic platforms like the Europa Lander or crewed missions with extended periods of dormancy such as Gateway. Gateway represents a vital component of NASA's Artemis program, which will serve as a multi-purpose orbital lunar outpost that provides essential support for a long-term human return to the lunar surface. It will serve as a staging point for deep space exploration. Autonomous Systems technologies provide the means of migrating mission control from Earth to spacecraft, habitats, and robotic explorers. This is enhancing for missions in the Earth-Lunar neighborhood and enabling for deep space missions. Long communication delays, for example up to 42 minutes round-trip between Earth and Mars, do not permit time-critical control decisions to be made from Earth mission control centers. Rather, time-critical control decisions for spacecraft operating in deep space must be made by onboard humans, by autonomous systems, or by some combination of astronaut-automation teaming. Long-term crewed spacecraft and habitats, such as the International Space Station, are so complex that a significant portion of the crew's time is spent keeping it operational even under nominal conditions in low-Earth orbit, while still requiring significant real-time support from Earth. The considerable challenge is to migrate the knowledge and capability embedded in current Earth mission control, with tens to hundreds of human specialists ready to provide instant knowledge, to onboard automation that teams with astronauts to autonomously manage spacecraft and habitats. For outer planet robotic explorers, the technical challenge is to develop cognitive systems to provide astronauts with improved situational awareness and autonomous systems that can rapidly respond to dynamic environments. Specific innovations being sought in this solicitation are described below: Neural net software pipelines and radiation hard neuromorphic processing hardware to support in-space autonomy and cognition. Advances in signal and data processing for neuromorphic processors promise to enable artificial intelligence and machine learning for autonomous spacecraft operations. Intelligent autonomous agent cognitive architectures are sought after as an onboard spacecraft capability to enable decision-making under uncertainty and to improve system performance through learning over time. Onboard fault management capabilities, such as onboard sensing, computing, algorithms, and models to improve the prognostic health management of future spacecraft. Multi-agent Cyber-Physical-Human (CPH) systems that operate autonomously from humans or under human direction. This capability will help to address the need for integrated data uncertainty management and a robust representation of trustworthy and trusted autonomy in space. Technologies for the control and coordination of swarms of planetary rovers, flyers, or in-space vehicles for future space missions. Autonomy and artificial intelligence technologies for Gateway operations and health management, for either fully autonomous or crew-supervised operations. The descriptions and references of each subtopic provide further detail to guide the development of proposals.