T Johnson
A. James and Alice B. Clark Foundation Chancellor Faculty Fellow
Associate Professor of Computer Science (CS), Computer Engineering (CmpE), and Electrical Engineering (EE)
Director of Graduate Studies (CS PhD)
Senior Research Scientist (VU-ISIS)
Taylor T. Johnson, PhD, PE (TN), is A. James and Alice B. Clark Foundation Chancellor Faculty Fellow, Director of Graduate Studies (CS PhD), and Associate Professor of Computer Science (CS), Computer Engineering (CmpE), and Electrical Engineering (EE) in the Departments of Computer Science and Electrical & Computer Engineering (ECE) (previously the Department of Electrical Engineering and Computer Science (EECS)) in the School of Engineering (VUSE) at Vanderbilt University (since August 2021, Assistant Professor 2016-2021), where he directs the Verification and Validation for Intelligent and Trustworthy Autonomy Laboratory (VeriVITAL) and is a Senior Research Scientist in the Institute for Software Integrated Systems (ISIS) and a Faculty Affiliate of the Data Science Institute (DSI). Taylor was previously an Assistant Professor of Computer Science and Engineering (CSE) at the University of Texas at Arlington (September 2013 to August 2016). Taylor earned a PhD in Electrical and Computer Engineering (ECE) from the University of Illinois at Urbana-Champaign in 2013, where he worked in the Coordinated Science Laboratory with Prof. Sayan Mitra, and earlier earned an MSc in ECE at Illinois in 2010 and a BSEE from Rice University in 2008. Taylor's research focus is developing formal verification techniques and software tools for cyber-physical systems (CPS), with a focus most recently on autonomous CPS that incorporate artificial intelligence (AI) and machine learning (ML) components, such as neural networks, for tasks ranging from sensing/perception through planning/control. Taylor has published around a hundred papers on these methods and their applications across CPS domains, such as power and energy systems, aerospace and avionics systems, automotive systems, transportation systems, and robotics, three of which were recognized with best/outstanding paper awards, from the IEEE and IFIP, and two of which were awarded Best Software Repeatability/Artifact Awards. Taylor's research aims to develop reliable embedded and cyber-physical systems by advancing and applying techniques and tools from formal methods, control theory, embedded systems, and software engineering. Taylor received the AFOSR Summer Faculty Fellowship Program (SFFP) award to visit the Air Force Research Laboratory (AFRL)'s Information Directorate in 2015, was a Visiting Faculty Research Program (VFRP) award fellow at AFRL's Information Directorate in 2014, and was a visiting graduate research assistant through an SFFP award at AFRL's Space Vehicles Directorate at Kirtland Air Force Base in 2011. Taylor is a 2018 and 2016 recipient of the AFOSR Young Investigator Program (YIP) award, a 2015 recipient of the NSF Computer and Information Science and Engineering (CISE) Research Initiation Initiative (CRII), and his research is / has been supported by AFRL, AFOSR, ARO, DARPA, NSA, NSF (CISE CCF/SHF, CNS/CPS; ENG ECCS/EPCN), NVIDIA, ONR, Toyota, and USDOT. Taylor has served on program committees and in different organizational roles for venues such as AAAI, CAV, CVPR, EMSOFT, FORMATS, HSCC, ICCV, NFM, SAIV, SPIN, RTSS, UAI, among many others, and is an Associate Editor of Software Tools for Technology Transfer (STTT). Taylor is co-founder of the Verification of Neural Networks Competition (VNN-COMP) and the International Competition on Verifying Continuous and Hybrid Systems (ARCH-COMP) category on Artificial Intelligence and Neural Network Control Systems (AINNCS).
Projects
- Collaborative Research: Operator theoretic methods for identification and verification of dynamical systems
- FMitF: Track II: Hybrid and Dynamical Systems Verification on the CPS-VO
- SHF: Small: Collaborative Research: Fuzzing Cyber-Physical System Development Tool Chains with Deep Learning (DeepFuzz-CPS)
- Understandable and Reusable Formal Verification for Cyber-Physical Systems
- FMitF: Track I: Generative Neural Network Verification in Medical Imaging Analysis
- Verification of Autonomous Systems: Hyperproperties in Machine Learning
- Collaborative Research: Operator theoretic methods for identification and verification of dynamical systems
- Collaborative Research: FMitF: Track II: Enhancing the Neural Network Verification (NNV) Tool for Industrial Applications
- High-Performance Computing for Neural Network Verification
Areas of Expertise
formal methods, formal verification, cyber-physical systems, autonomy, safe artificial intelligence (AI), trustworthy AI, machine learning, hybrid systems