Assistant Professor of Computer Science and Electrical and Computer Engineering-Systems
BiographyI am an Assistant Professor at the Department of Computer Science at the University of Southern California. From 2020-2022, I was a postdoctoral researcher at the University of Pennsylvania. From 2016-2020, I conducted my PhD studies in Electrical Engineering at KTH Royal Institute of Technology (Stockholm, Sweden). My research interests include systems & control theory, formal methods, and autonomous systems. I received the Best Student Paper Award at the 2021 Conference on Decision and Control (as a co-author) and the Outstanding Student Paper Award at the 2019 Conference on Decision and Control. I was a finalist for the Best Paper Award at the 2022 Conference on Hybrid Systems: Computation and Control, and for the Best Student Paper Award at the 2018 American Control Conference.
The recent computational advances in artificial intelligence (AI) and machine learning promise to enable many future technologies such as autonomous driving, smart home technologies, human-assisted robotics, and smart healthcare. Over the next decade, large amounts of data will be generated and stored as devices that control and sense the physical world are becoming more affordable, e.g., robots, smart watches. While the availability of data creates many exciting opportunities, it also gives rise to fundamental research challenges on the interface between control theory, machine learning and AI, and formal methods. Not only are new theoretical frameworks needed to address these new research challenges, but wide availability of these future systems and technologies will also require more efficient computational approaches that allow for near real-time learning and control. The key research challenges that I focus on include the development of new theoretical and computational frameworks for:
- more efficient and safe use of data for the control of data-driven intelligent systems,
- risk-aware verification and control of complex AI-enabled autonomous systems,
- efficient planning and control under formal high-level system specifications, and
- addressing the growing complexities that arise from the combination of data, formal high-level system specifications, and the interplay between autonomy and humans-in-the-loop.
While there has been tremendeous success over the past years towards creating data-driven intelligent systems, there is still a lack of understanding of the complex interplay between the fields of control theory, machine learning and AI, and formal methods. My research helps to bridge these fields towards the design of scalable data-driven intelligent systems. Specifically, my personal research agenda revolves around safe and distributed AI-enabled autonomous systems with a focus on addressing the aforementioned key challenges. My contributions span the development of theoretical frameworks with stringent performance and safety guarantees to their scalable implementation by means of distributed computationally efficient algorithms.