Currently, there is no governing standard that addresses the safe integration of AI into computer-based control systems (CBCS) in human spaceflight. The computer-based control expectations of those safety-critical systems on the International Space Station (ISS) are captured in SSP 50038, Computer-Based Control System Safety Requirements, with one caveat: the standard was not designed with AI applications in mind. SSP 50038 does not cover the probabilistic behavior, opacity, and training-data dependency of modern AI/ML systems. The objectives of this work is to develop an AI taxonomy relevant to safety characteristics (determinism, transparency, data dependency, failure predictability), systematically map AI characteristics against SSP 50038, propose a requirements framework that defines a safe operating envelope for AI within CBCS, demonstrate the requirement application within Environmental Control and Life Support System (ECLSS) cases, and validate the framework through gap analysis against SSP 50038 and cross-domain approaches (EASA AI Roadmap, ISO 21448/SOTIF, and UL 4600). This thesis presents one of the first systems-engineering approaches to address AI in safety-critical systems for human spaceflight. The requirements framework illustrates conditional suitability and restrictions for each AI category. Lastly, the framework proves to extend and fill gaps in the space domain while being consistent with cross-domain standards.
","abstract_html":"<p>Currently, there is no governing standard that addresses the safe integration of AI into computer-based control systems (CBCS) in human spaceflight. The computer-based control expectations of those safety-critical systems on the International Space Station (ISS) are captured in SSP 50038, Computer-Based Control System Safety Requirements, with one caveat: the standard was not designed with AI applications in mind. SSP 50038 does not cover the probabilistic behavior, opacity, and training-data dependency of modern AI/ML systems. The objectives of this work is to develop an AI taxonomy relevant to safety characteristics (determinism, transparency, data dependency, failure predictability), systematically map AI characteristics against SSP 50038, propose a requirements framework that defines a safe operating envelope for AI within CBCS, demonstrate the requirement application within Environmental Control and Life Support System (ECLSS) cases, and validate the framework through gap analysis against SSP 50038 and cross-domain approaches (EASA AI Roadmap, ISO 21448/SOTIF, and UL 4600). This thesis presents one of the first systems-engineering approaches to address AI in safety-critical systems for human spaceflight. The requirements framework illustrates conditional suitability and restrictions for each AI category. Lastly, the framework proves to extend and fill gaps in the space domain while being consistent with cross-domain standards.</p>","abstract_has_math":false,"creators":["Bosch, Liz"],"institution":null,"degree_name":"Master of Systems Engineering","degree_level":"Thesis - Open Access","degree_discipline":"Electrical, Computer, Software, and Systems Engineering","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-04-01T07:00:00Z","date_published":"2026-04-01T07:00:00Z","updated_at":"2026-07-27T19:26:22Z","subjects":["AI-enabled computer-based control system / AI-CBCS","Computer-Based Control System (CBCS)","safety-critical systems","human spaceflight safety","crewed spaceflight","requirements framework","requirements engineering","AI certification","AI safety assurance","AI integration in safety-critical systems","Space Habitation and Life Support","Space Vehicles","Systems Engineering","Systems Engineering and Multidisciplinary Design Optimization"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.erau.edu/edt/997","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Bosch, Liz"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical, Computer, Software, and Systems Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Systems Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["AI-enabled computer-based control system / AI-CBCS","Computer-Based Control System (CBCS)","safety-critical systems","human spaceflight safety","crewed spaceflight","requirements framework","requirements engineering","AI certification","AI safety assurance","AI integration in safety-critical systems","Space Habitation and Life Support","Space Vehicles","Systems Engineering","Systems Engineering and Multidisciplinary Design Optimization"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.erau.edu/edt/997"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Currently, there is no governing standard that addresses the safe integration of AI into computer-based control systems (CBCS) in human spaceflight. The computer-based control expectations of those safety-critical systems on the International Space Station (ISS) are captured in SSP 50038, Computer-Based Control System Safety Requirements, with one caveat: the standard was not designed with AI applications in mind. SSP 50038 does not cover the probabilistic behavior, opacity, and training-data dependency of modern AI/ML systems. The objectives of this work is to develop an AI taxonomy relevant to safety characteristics (determinism, transparency, data dependency, failure predictability), systematically map AI characteristics against SSP 50038, propose a requirements framework that defines a safe operating envelope for AI within CBCS, demonstrate the requirement application within Environmental Control and Life Support System (ECLSS) cases, and validate the framework through gap analysis against SSP 50038 and cross-domain approaches (EASA AI Roadmap, ISO 21448/SOTIF, and UL 4600). This thesis presents one of the first systems-engineering approaches to address AI in safety-critical systems for human spaceflight. The requirements framework illustrates conditional suitability and restrictions for each AI category. Lastly, the framework proves to extend and fill gaps in the space domain while being consistent with cross-domain standards.
"]},{"key":"dc:title","label":"Title","values":["Artificial Intelligence in Human Spaceflight Safety-Critical Systems: A Requirements Framework for AI-Enabled Computer-Based Control Systems"]}]}],"canonical_facts":{"dc:creator":["Bosch, Liz"],"dc:description.abstract":["Currently, there is no governing standard that addresses the safe integration of AI into computer-based control systems (CBCS) in human spaceflight. The computer-based control expectations of those safety-critical systems on the International Space Station (ISS) are captured in SSP 50038, Computer-Based Control System Safety Requirements, with one caveat: the standard was not designed with AI applications in mind. SSP 50038 does not cover the probabilistic behavior, opacity, and training-data dependency of modern AI/ML systems. The objectives of this work is to develop an AI taxonomy relevant to safety characteristics (determinism, transparency, data dependency, failure predictability), systematically map AI characteristics against SSP 50038, propose a requirements framework that defines a safe operating envelope for AI within CBCS, demonstrate the requirement application within Environmental Control and Life Support System (ECLSS) cases, and validate the framework through gap analysis against SSP 50038 and cross-domain approaches (EASA AI Roadmap, ISO 21448/SOTIF, and UL 4600). This thesis presents one of the first systems-engineering approaches to address AI in safety-critical systems for human spaceflight. The requirements framework illustrates conditional suitability and restrictions for each AI category. Lastly, the framework proves to extend and fill gaps in the space domain while being consistent with cross-domain standards.
"],"dc:identifier":["https://commons.erau.edu/edt/997"],"dc:subject":["AI-enabled computer-based control system / AI-CBCS","Computer-Based Control System (CBCS)","safety-critical systems","human spaceflight safety","crewed spaceflight","requirements framework","requirements engineering","AI certification","AI safety assurance","AI integration in safety-critical systems","Space Habitation and Life Support","Space Vehicles","Systems Engineering","Systems Engineering and Multidisciplinary Design Optimization"],"dc:title":["Artificial Intelligence in Human Spaceflight Safety-Critical Systems: A Requirements Framework for AI-Enabled Computer-Based Control Systems"],"thesis:degree_discipline":["Electrical, Computer, Software, and Systems Engineering"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Systems Engineering"]},"updated_at":"2026-07-27T19:26:22Z"}