Verified Artificial Intelligence and Autonomy
Virtual seminars Computer Science: Joint ICE-TCS and GSSI - Sanjit A. Seshia (UC Berkeley, USA)
Schedule: 30 June, 15:00 GMT/16:00 BST/17:00 Italian time
Virtual link: https://berkeley.zoom.us/j/94918134773?pwd=aStLc0ZVcFVxd2RzMGdDZkZNTnFBQT09
Speaker: Sanjit A. Seshia (UC Berkeley, USA) WWW: http://people.eecs.berkeley.edu/~sseshia/
Biographical sketch: https://people.eecs.berkeley.edu/~sseshia/bio.html
Title: Verified Artificial Intelligence and Autonomy
Abstract: Verified artificial intelligence (AI) is the goal of designing AI-based systems that have strong, verified assurances of correctness with respect to mathematically-specified requirements. This goal is particularly important for autonomous and semi-autonomous systems. In this talk, I will consider Verified AI from a formal methods perspective and with a special focus on autonomy. I will describe the challenges for and recent progress towards attaining Verified AI, with examples from the domain of intelligent cyber-physical systems, with a particular focus on autonomous vehicles and aerospace systems.