Trustworthy autonomous Vehicles at a Large Scale, Safety, Generalization, and Social Good

As AI becomes more integrated into physical autonomy, it presents a dual spectrum of opportunities and risks. In this talk, I will introduce our efforts in deploying trustworthy intelligent autonomy at a large scale for vital civil usage such as self-driving cars, assistant robots, and first responders to emergencies. During the deployment and transition, training data often exhibit significant imbalance, multi-modal complexity, and nonstationarity. I will initiate the discussion by analyzing ‘long-tailed’ problems with rare events and their connection to safety evaluation and safe reinforcement learning. I will then discuss how modeling multi-modal uncertainties as ‘tasks’ may enhance generalizability by learning across domains. In cases involving unknown-unknown tasks with severely limited data, we explore the potential of leveraging external knowledge from legislative sources, causal reasoning, and large language models. Lastly, I will discuss the potential social benefits/concerns regarding deploying intelligent autonomy at a large scale. Applications cover self-driving and assistant robots.

Speaker: Ding Zhao, Carnegie Mellon University