ABSTRACT:

As people rush to integrate Artificial Intelligence (AI) into real-world systems in consequential domains such as autonomous transportation, smart manufacturing, and healthcare, researchers and engineers are facing calls to ensure that these systems are not only autonomous but also “trustworthy”. In this talk, Dr. Zhao will introduce two key building blocks to build trustworthy AI and their applications on autonomous vehicles: a) generation of realistic safety-critical digital twins to support design and tests of complex AI systems. b) development of robust, safe, and generalizable AI for decision-making and vision algorithms. Our related papers were summarized on these three webpages: generating safety-critical digital twins, certifiable evaluation and trustworthy autonomy.

Short Bio:

Ding Zhao gets his PhD from the University of Michigan, Ann Arbor. He is currently an assistant professor in the Department of Mechanical Engineering at the Carnegie Mellon University, with affiliation at Computer Science Department, Machine Learning Department, and Robotics Institute. His research focuses on both the theoretical and practical aspects of trustworthy AI with applications on autonomous vehicles, smart manufacturing, intelligent transportation, assistant robots, healthcare diagnosis, and cybersecurity. He is the recipient of the MIT Technology Review 35 under 35 China Award, National Science Foundation CAREER Award, Ford University Collaboration Award, Carnegie-Bosch Research Award, Struminger Teaching Award, and industrial fellowship awards from Adobe, Bosch, and Toyota. He works with leading industrial partners, including Google Brain, Amazon, Ford, Uber, IBM, Adobe, Bosch, and Rolls-Royce.

This event will also be live-streamed online, scan to view: