Report Title: Safety Design and Verification of Learning enabled Cyber Physical Systems

Reported by: Huang Chao, University of Liverpool, UK

Report time: May 24, 2021 13:30

Report location: B1002, Science Building

Host: Yang Zhengfeng

Abstract:

Learning-enabled CPSs have been receiving numerous attractions from both academia and industry due to promising applications.

They often leverage machine learning techniques in their perception of the environment, and increasingly also in the consequent decision making process for planning, navigation, control, etc. With no doubt, safety is one of the key issues before such systems are applied in practice.  In this talk, I will introduce our recent works on safety verification and design of learning-enabled systems with respect to perception,  adaptation, control and its timing impact on overall execution with theoretical guarantees. This talk aims to provide some insights  on mathematical foundation of machine learning from the perspective of formal methods.Prof. Chao Huang will join the University of Liverpool this June as a lecturer in aritificial intelligence. He is now a postdoc at the Department of Electrical and Computer Engineering (ECE) in Northwestern University.

Introduction of Lectuer:

Prof. Huang received a Ph.D. and a B.E. in CS from Nanjing University in 2018 and 2011 respectively. His research interests include verification and design of intelligent systems, including Learning-Enabled Cyber-Physical Systems (LE-CPS), real-time systems, embedded systems, and various applications, such as autonomous driving and mobile robot navigation. He has published more than 20 articles at top-tier conferences and journals on machine learning safety, e.g., CAV, HSCC, EMSOFT, FM, IJCAI, ICRA, DAC, ICCAD, TECS, TCAD. His paper at ICCAD 2020 was selected as Best Paper Candidate. He also served as a PC member on the conferences, e.g., RTSS, HSCC, SETTA.