Abstract: Using advanced 3D sensors and sophisticated deep learning models, autonomous systems such as self-driving cars, delivery drones are already transforming our daily life. However, a significant remaining challenge for further advancement is the reliability, robustness, and the ability to anticipate and handle long-tail events and corner-cases. Humans, on the other hand, are extremely good at handling corner-cases, so if autonomous systems are to be widely accepted, they must achieve human-level reliability. In this talk, I will present a series of systems research, through the lens of autonomous cars, that leverages cooperative autonomy and edge ML ecosystems to enhance the robustness across the autonomous systems stack.