Cognitive assistants are intelligent agents that support and “augment” humans in various tasks. They often provide a natural language interface so you can speak to them like you would speak to your colleague.
Daphne is, to the best of our knowledge, the first cognitive assistant designed to support systems engineers and scientists during mission and concept studies and early formulation of Earth observation missions.
Early mission formulation is challenging mainly for two reasons: 1) the space of alternatives to consider is extremely large; 2) evaluating each alternative is challenging because there are many competing criteria, estimating performance requires running computationally expensive simulations, it often involves subjective preferences, and there is a lot of technical and programmatic uncertainty and ambiguity.
A snapshot of the Daphne cognitive assistant is shown below.
To support systems engineers in this task, Daphne integrates various tools developed in our lab in the last few years, including VASSAR (for mission evaluation), iFEED (for data analysis), and KDO\AOS (for optimization). It also has a copy of the CEOS database of all the Earth observing missions launched or planned to date.
Daphne is equipped with various skills, including: 1) The Engineer, which can answer questions about designing spacecraft and estimating their cost and performance; 2) The Analyst, which can mine the existing set of mission designs and answer statistical questions about it; 3) The Explorer, which searches the design space and can answer questions about how to search is progressing; 4) The Historian, which queries the CEOS database and can answer questions about past missions.
The overall architecture of Daphne is shown below.
Interested in learning more about Daphne? Check out the publications below or just try it by yourself at selva-research.com/daphne!
Bang, H., Viros, A., Prat, A., & Selva, D. (2018). Daphne : An Intelligent Assistant for Architecting Earth Observing Satellite Systems. 2018 AIAA Information Systems-AIAA Infotech @ Aerospace, AIAA SciTech Forum, 1–14. https://doi.org/10.2514/6.2018-1366
Viros Martin, A., & Selva, D. (2019). From Design Assistants to Design Peers: Turning Daphne into an AI Companion for Mission Designers. AIAA Information Systems-AIAA Infotech at Aerospace, 2019. https://doi.org/10.2514/6.2019-0402