Artificial intelligence costs, benefits, and risks for selected spacecraft ground system automation scenarios

Abstract In response to a number of high-level strategy studies in the early 1980s, Expert Systems and Artificial Intelligence (AI/ES) efforts for spacecraft ground systems have proliferated in the past several years primarily as individual small to medium scale applications. It is useful to stop and assess the impact of this technology in view of lessons learned to date and, hopefully, to determine if the overall strategies of some of the earlier studies both are being followed and still seem relevant. To achieve that end four idealized ground system automation scenarios and their attendant AI architectures are postulated and benefits, risks, and lessons learned are examined and compared. These architectures encompass: (1) no AI (baseline), (2) standalone expert systems, (3) standardized, reusable knowledge base management systems (KBMS), and (4) a futuristic unattended automation scenario. The resulting artificial intelligence lessons learned, benefits, and risks for spacecraft ground system automation scenarios are described.