Neural Network Verification for Autonomous Systems
Data-driven methods have proven very effective for control, planning and estimation onboard complex robotic systems. Unfortunately, the safety and reliability of the resulting system consequently becomes much more difficult to analyze. One answer to this problem is the small but growing body of work focused on formal verification of neural networks. However, many of the first works published in this area considered simple settings where the networks were analyzed in isolation. My PhD thesis, completed in 2022, and current research as a postdoctoral fellow focuses on developing methods to formally verify neural networks that are components within larger and more complex systems, such as control systems. In this talk, I will review some recent results from this body of work and discuss my research vision for the future.
Speaker Biography
Dr. Chelsea Sidrane (KTH Royal Institute of Technology)
Chelsea Sidrane is a Digital Futures Postdoctoral Research Fellow at KTH Royal Institute of Technology in the Division of Robotics, Perception, and Learning. In August 2022, she graduated with a PhD from the Stanford University Aerospace Engineering Department. Before that, she obtained her Bachelor's degree in mechanical engineering from Cornell University. She was born and raised in the suburbs of New York City. Broadly, her research interests are focused on control theory, robot planning, verification, uncertainty and risk awareness, and machine learning.
