Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute for Electrical & Computer Engineering Joint Seminar Series

Speaker: Mauricio Castillo-Effen, Fellow at Lockheed Martin Advanced Technology Laboratories

Talk Title: New Vistas in Autonomy Assurance

Series: EE598 Seminar Series

Abstract: Achieving trustworthiness is a major challenge preventing autonomous technologies from realizing their full potential in applications without an "undo" option for undesirable consequences. This talk argues that some obstacles to attaining assurance in autonomy result from applying traditional engineering and safety-critical system certification views and practices that are incompatible with the unique nature and potential use cases of modern autonomous systems. These systems are typically deployed in highly variable environments, which easily lead to violations of design assumptions. Additionally, autonomous systems consist of components that use hard-to-assure technologies, such as machine learning, and are also often built from components sourced from complex supply chains. This talk introduces assurance as an epistemic endeavor, emphasizing its value in designing and developing systems that are fit for purpose and use. We will then discuss the concept of agility and its role in reinterpreting the use and application of assurance cases for continuous assurance. This discussion will include the interpretation of context and operational domains. We will also describe a socio-technical solution, potentially enhanced by generative AI, to introduce assurance early in the system's lifecycle. Real-world examples from autonomous systems and applications studied at the Lockheed Martin Advanced Technology Laboratories will be used to illustrate these concepts throughout the presentation. Finally, we will highlight promising assurance technologies and identify gaps that require attention from the research community. By acknowledging these gaps, we hope to encourage further research and collaboration to address the challenges of assuring autonomous systems.

Biography: Mauricio Castillo-Effen is a Fellow at Lockheed Martin Advanced Technology Laboratories (LM ATL), where he leads the research area in Trustworthy AI and Autonomy (TAA). His team focuses on developing solutions for deploying complex decision-making technologies such as autonomy and artificial intelligence in high criticality applications. He collaborates closely with Lockheed Martin’s Business Areas to address challenges related to verification, validation, testing, evaluation, and certification. Previously, at General Electric, he led R&D efforts in aviation, aerial autonomy, and mining robotics, which led to the establishment of the robotics research laboratory and a spin-off company focused on robotic inspection, repair, and replacement. He has served as Principal Investigator and contributor for multiple R&D programs funded by DARPA, AFRL, NASA, and DHS, advancing the fields of autonomy, assurance, and certification in the aerospace industry. He has a background in systems theory, control and estimation, cyber-physical systems, embedded systems, and robotics. He has also taught controls and mechatronics at multiple universities worldwide. He holds more than twenty patents in robotics, autonomy, and aviation. Mauricio received his Ph.D. in Electrical Engineering from the University of South Florida

Host: Pierluigi Nuzzo

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

Audiences: Everyone Is Invited

Contact: Ariana Perez