On the Safety and Generalizability of Trustworthy Intelligent Autonomy

2022年12月22日

As machine learning has started to shift towards deployment in the physical world, its rapid development is coupled with as much risk as benefits. In this talk, I will discuss two key aspects of developing trustworthy autonomy: generalizability and safety. I will introduce our recent progress in both mathematical foundations and real-world applications. I will also share the lessons we learned and our outlook for future research directions.