Research
The research my group is currently conducting spans over machine learning, formal methods, and robotics. If you are interested in these areas and want to collaborate with us, please feel free to get in touch.
Specifically, we are interested in analysing autonomous systems -- systems that can learn, adapt, and make decisions by themselves -- in terms of their properties (e.g., safety, robustness, trustworthiness, security, etc), to understand if they are applicable to safety critical applications, and constructing autonomous systems with these properties satisfied. This may include (but not limited to)
1. verification of neural network-based deep learning on safety and security properties,
2. practical analysis techniques (software testing, safety argument, certification, etc) for machine learning techniques,
3. interpretation and explanation of deep learning, and
4. logic-based approaches for the specification, verification and synthesis of autonomous multi-agent systems.
Currently, the application areas we are addressing include self-driving cars, underwater vehicles, and other robotics applications. We are also interested in various healthcare applications where safety and interpretability are important.
The research has been funded by Dstl, EPSRC, European Commission, etc. I have been the PI (or Liverpool PI) for projects valued more than £1.86M, and co-I for more than £15M. I am directing the Autonomous Cyber Physical Systems Laboratory (https://cgi.csc.liv.ac.uk/~acps/index.html), which is now at Ashton Building and will be re-located to the new Digital Innovation Facility (DIF) Building.
Research grants
Safety Assurance for Autonomous Underwater Vehicle
DEFENCE SCIENCE & TECHNOLOGY LABORATORY (UK)
October 2020 - October 2022
Test Coverage Metrics for AI – v2.0
DEFENCE SCIENCE & TECHNOLOGY LABORATORY (UK)
October 2019 - March 2021
ITT for Test Metrics for Artificial Intelligence
DEFENCE SCIENCE & TECHNOLOGY LABORATORY (UK)
May 2018 - March 2020
Utilising generative AI, specifically large language models (LLMs) for the searching of technical documentation in a cyber-secure environment
INNOVATE UK (UK), LEONARDO UK LIMITED (UK)
March 2024 - July 2024
Generative LLMs for responsible safety engineering
BRITISH ACADEMY (UK)
March 2025 - March 2026
ARRES FORECAST: an AI-driven platform to predict road defect evolution
INNOVATE UK (UK)
October 2024 - March 2025
Robustifying generative AI through human-centric integration of neural and symbolic methods (ROBUSTIFAI)
EUROPEAN COMMISSION
June 2025 - May 2028
SPACE: Fully Decentralised Distributed Learning
INNOVATE UK (UK)
October 2022 - March 2024