The use of autonomous flight vehicles has recently increased due to their versatility and capability of carrying out different type of missions in a wide range of flight conditions. Adequate commanded trajectory generation and modification, as well as high-performance trajectory tracking control laws have been an essential focus of researchers given that integration into the National Air Space (NAS) is becoming a primary need. However, the operational safety of these systems can be easily affected if abnormal flight conditions are present, thereby compromising the nominal bounds of design of the system's flight envelop and trajectory following. This thesis focuses on investigating methodologies for modeling, prediction, and protection of autonomous vehicle trajectories under normal and abnormal flight conditions. An Artificial Immune System (AIS) framework is implemented for fault detection and identification in combination with the multi-goal Rapidly-Exploring Random Tree (RRT*) path planning algorithm to generate safe trajectories based on a reduced flight envelope. A high-fidelity model of a fixed-wing unmanned aerial vehicle is used to demonstrate the capabilities of the approach by timely generating safe trajectories as an alternative to original paths, while integrating 3D occupancy maps to simulate obstacle avoidance within an urban environment.
","abstract_html":"<p>The use of autonomous flight vehicles has recently increased due to their versatility and capability of carrying out different type of missions in a wide range of flight conditions. Adequate commanded trajectory generation and modification, as well as high-performance trajectory tracking control laws have been an essential focus of researchers given that integration into the National Air Space (NAS) is becoming a primary need. However, the operational safety of these systems can be easily affected if abnormal flight conditions are present, thereby compromising the nominal bounds of design of the system's flight envelop and trajectory following. This thesis focuses on investigating methodologies for modeling, prediction, and protection of autonomous vehicle trajectories under normal and abnormal flight conditions. An Artificial Immune System (AIS) framework is implemented for fault detection and identification in combination with the multi-goal Rapidly-Exploring Random Tree (RRT*) path planning algorithm to generate safe trajectories based on a reduced flight envelope. A high-fidelity model of a fixed-wing unmanned aerial vehicle is used to demonstrate the capabilities of the approach by timely generating safe trajectories as an alternative to original paths, while integrating 3D occupancy maps to simulate obstacle avoidance within an urban environment.</p>","abstract_has_math":false,"creators":["Morillo, Eduardo"],"institution":null,"degree_name":"Master of Science in Aerospace Engineering","degree_level":"Thesis - Open Access","degree_discipline":"Aerospace Engineering","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-12-15T08:00:00Z","date_published":"2022-12-15T08:00:00Z","updated_at":"2026-07-27T19:25:10Z","subjects":["UAV","fixed-wing","path planning","fault tolerance","flight envelope reduction","Rapidly Exploring Random Trees","aileron failures","artificial immune system","health monitoring system","nonlinear dynamic inversion controller","urban environment","artificial intelligence","unmanned systems","Aeronautical Vehicles","Controls and Control Theory","Navigation, Guidance, Control and Dynamics","Navigation, Guidance, Control, and Dynamics","Systems Engineering and Multidisciplinary Design Optimization"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://commons.erau.edu/edt/714","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Morillo, Eduardo"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Aerospace Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Aerospace Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["UAV","fixed-wing","path planning","fault tolerance","flight envelope reduction","Rapidly Exploring Random Trees","aileron failures","artificial immune system","health monitoring system","nonlinear dynamic inversion controller","urban environment","artificial intelligence","unmanned systems","Aeronautical Vehicles","Controls and Control Theory","Navigation, Guidance, Control and Dynamics","Navigation, Guidance, Control, and Dynamics","Systems Engineering and Multidisciplinary Design Optimization"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://commons.erau.edu/edt/714"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The use of autonomous flight vehicles has recently increased due to their versatility and capability of carrying out different type of missions in a wide range of flight conditions. Adequate commanded trajectory generation and modification, as well as high-performance trajectory tracking control laws have been an essential focus of researchers given that integration into the National Air Space (NAS) is becoming a primary need. However, the operational safety of these systems can be easily affected if abnormal flight conditions are present, thereby compromising the nominal bounds of design of the system's flight envelop and trajectory following. This thesis focuses on investigating methodologies for modeling, prediction, and protection of autonomous vehicle trajectories under normal and abnormal flight conditions. An Artificial Immune System (AIS) framework is implemented for fault detection and identification in combination with the multi-goal Rapidly-Exploring Random Tree (RRT*) path planning algorithm to generate safe trajectories based on a reduced flight envelope. A high-fidelity model of a fixed-wing unmanned aerial vehicle is used to demonstrate the capabilities of the approach by timely generating safe trajectories as an alternative to original paths, while integrating 3D occupancy maps to simulate obstacle avoidance within an urban environment.
"]},{"key":"dc:title","label":"Title","values":["On-Board Artificial Intelligence for Failure Detection and Safe Trajectory Generation"]}]}],"canonical_facts":{"dc:creator":["Morillo, Eduardo"],"dc:description.abstract":["The use of autonomous flight vehicles has recently increased due to their versatility and capability of carrying out different type of missions in a wide range of flight conditions. Adequate commanded trajectory generation and modification, as well as high-performance trajectory tracking control laws have been an essential focus of researchers given that integration into the National Air Space (NAS) is becoming a primary need. However, the operational safety of these systems can be easily affected if abnormal flight conditions are present, thereby compromising the nominal bounds of design of the system's flight envelop and trajectory following. This thesis focuses on investigating methodologies for modeling, prediction, and protection of autonomous vehicle trajectories under normal and abnormal flight conditions. An Artificial Immune System (AIS) framework is implemented for fault detection and identification in combination with the multi-goal Rapidly-Exploring Random Tree (RRT*) path planning algorithm to generate safe trajectories based on a reduced flight envelope. A high-fidelity model of a fixed-wing unmanned aerial vehicle is used to demonstrate the capabilities of the approach by timely generating safe trajectories as an alternative to original paths, while integrating 3D occupancy maps to simulate obstacle avoidance within an urban environment.
"],"dc:identifier":["https://commons.erau.edu/edt/714"],"dc:subject":["UAV","fixed-wing","path planning","fault tolerance","flight envelope reduction","Rapidly Exploring Random Trees","aileron failures","artificial immune system","health monitoring system","nonlinear dynamic inversion controller","urban environment","artificial intelligence","unmanned systems","Aeronautical Vehicles","Controls and Control Theory","Navigation, Guidance, Control and Dynamics","Navigation, Guidance, Control, and Dynamics","Systems Engineering and Multidisciplinary Design Optimization"],"dc:title":["On-Board Artificial Intelligence for Failure Detection and Safe Trajectory Generation"],"thesis:degree_discipline":["Aerospace Engineering"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science in Aerospace Engineering"]},"updated_at":"2026-07-27T19:25:10Z"}