Xiaowei Huang

Professor Xiaowei Huang serves as Professor of Computer Science at the University of Liverpool within the School of Electrical Engineering, Electronics and Computer Science. He leads the Trustworthy Autonomous Cyber Physical System Lab, focusing on critical research at the intersection of machine learning, formal methods, and robotics. His work addresses fundamental challenges in autonomous systems that learn, adapt, and make decisions independently.

Dr. Huang's research interests center on trustworthy AI with specific expertise in verification, explainable AI, and AI safety and security. His group investigates autonomous systems' properties including safety, robustness, trustworthiness, and security to determine their applicability in safety-critical environments. This encompasses neural network verification, practical analysis techniques for machine learning, deep learning interpretation, and logic-based approaches for multi-agent autonomous systems.

His recent publications reveal strong trends in autonomous driving safety verification, robust computer vision systems, and neural-symbolic integration. The research spans multiple application domains including self-driving cars, underwater vehicles, robotics, and healthcare systems where safety and interpretability are paramount. His work demonstrates consistent focus on practical verification frameworks and robustness assessment methodologies.

As Principal Investigator or Liverpool PI, Dr. Huang has secured over £1.86M in research funding from prestigious sources including Dstl, EPSRC, and the European Commission, with additional co-investigator roles totaling over £15M. Current projects include Safety Assurance for Autonomous Underwater Vehicles and Test Coverage Metrics for AI. He directs the Autonomous Cyber Physical Systems Laboratory, soon to be relocated to the new Digital Innovation Facility Building.

Dr. Huang serves as Module Co-ordinator for Advanced Artificial Intelligence (COMP219) and supervises numerous PhD students working on topics including uncertainty analysis in data, autonomous vehicle perception, graph neural networks, and reliable deep learning models. His laboratory provides a research environment focused on bridging theoretical foundations with practical safety-critical applications.