Dr Maria Chli
Reader, Applied Artificial Intelligence and Robotics Aston University
- Birmingham
Dr Chli works on artificial intelligence, machine learning and multi-agent systems, focusing on smart cities and transport optimisation.
Media
Social
Biography
She has authored publications in top-tier journals and A1-ranked conferences such as Journal of Artificial Intelligence Research, IEEE Transactions on Systems, Man, and Cybernetics, AAMAS, IJCAI, and ITSC. Her research has been applied to manage real traffic networks in Coventry, demonstrating the practical impact of her AI methods, and has been featured in BBC News, Deutsche Welle, and Radio New Zealand.
Dr Chli has successfully led and supervised numerous PhD projects and has secured over £3M in research funding across national and international programmes. She serves as an expert for EPSRC, the European Commission, and IFAAMAS, contributing to strategic research and funding decisions in AI and autonomous systems.
As founder and leader of the Computer Science Industry Club, Dr. Chli has fostered research collaborations with a mix of large corporations and agile high-tech SMEs. These partnerships have enabled applied research, industrially relevant projects, and strong student engagement.
Her research bridges rigorous AI theory with real-world deployment, advancing multi-agent systems, intelligent transport, and complex systems modelling while linking academia, industry, and policy at national and international levels.
Areas of Expertise
Accomplishments
Funding
Received £2.4m of research funding. As industrial liaison, doubled department's industrial research funding (£6.3m in six years)
REF 2021
Published two 4* and at least eight 3* papers.
Founder
Founder of multi-award-winning CS Industry Club scheme.
Education
Aston University
Certificate
Learning and Teaching in Higher Education
2007
Imperial College London
PhD
Intelligent Systems
2005
Imperial College London
MEng
Computing
2001
Affiliations
- ALICE Research Group, Systems Analytics Research Institute, SARI.
Links
Media Appearances
Can we make traffic jams a thing of the past?
RNZ radio
2022-06-26
Here's a glimpse of the future, finally, the world's first traffic control system of its kind, they say, using artificial intelligence, designed to make urban traffic jams a thing of the past.
Computer scientist Dr Maria Chli joins Jim from Aston University in Birmingham.
Aston University develops AI traffic lights in bid to cut queues
BBC online
2022-05-13
"We have set this up as a traffic control game. The program gets a 'reward' when it gets a car through a junction," Dr Maria Chli, reader in Computer Science at Aston University in Birmingham, explained.
AI traffic light system could make traffic jams a distant memory
EurekAlert! online
2022-05-11
Dr Maria Chli, reader in Computer Science at Aston University, explained: “We have set this up as a traffic control game. The program gets a ‘reward’ when it gets a car through a junction. Every time a car has to wait or there’s a jam, there’s a negative reward. There’s actually no input from us; we simply control the reward system.”
Smart traffic lights that could prevent traffic jams
Deutsche Welle
2022-05-05
"We've set it up like a traffic control game. The program receives a 'reward' when it gets a car to pass through an intersection," explained Dr. Maria Chli, a lecturer in Computer Science at Aston University.
[Translated from Spanish]
Traffic jams at junctions
BBC online
2022-11-03
Long queues at traffic lights could be a thing of the past, thanks to a new artificial intelligence system developed by Aston University researchers.
Research Focus
JOURNAL PUBLICATIONS
1. Deep Reinforcement Learning traffic signal controller for large, real-world traffic networks. Women in Engineering and Science: AI and Sustainability. Springer, 2025.
2. Development and functional testing of FeedQuest: an interactive, virtual laboratory to explore mealtime effects on children’s dietary intakes as a dynamic system, Appetite (189), 106713, Elsevier, 2023. IF: 5.4 (Q1 in both Psychology and Nutrition & Dietetics)
3. Optimal and Efficient Auctions for the Gradual Procurement of Strategic Service Provider Agents, Journal of Artificial Intelligence Research (76), pp. 959-1018, 2023. IF: 5 (top 18% in Computer Science – Artificial Intelligence). This work was inspired by Chli and Winsper (2015) and earlier papers, for which I have been interviewed by Faculti.net in 2023.
ARTICLES IN BLIND PEER-REVIEWED CONFERENCES
1. Robust Information Design for Multi-Agent Systems with Complementarities: Smallest-Equilibrium Threshold Policies, Proceedings of the International Conference of Autonomous Agents and Multiagent Systems– AAMAS 2026 (
Research Grants
Knowledge Transfer Partnership with Rimilia Holdings
Innovate UK
2017-2020
“Predictive Analytics for debtor payment behaviour modelling”, funded a postdoctoral associate to analyse company networks, model payment behaviour, and develop policies for prompt payment using machine learning and agent-based modelling.
Knowledge Transfer Partnership with PrecisionLife
Innovate UK
2019-2022
“Edge Analytics for Assisted Independent Living” funded a postdoctoral associate to analyse multimodal data to extend our modelling and decision-making research into healthcare.
AXA Research Fellowship
AXA Research Fund
2019-2022
“Agent-Based Modelling for Early Child Diet Quality” hosted Dr. M. Jarman (now a Lecturer) in collaboration with J. Blissett (LHS). Inspired by my work in agent-based modelling for policy and behaviour, it delivered key modelling tools to nutrition and health.
Newton International Fellowship
The Royal Society
2020-2022
“Empowering Automatic Strategic Supply Chains” hosted Dr F. Farhadi (now a Lecturer), developing a decentralised mechanism for efficient supply chain formation. Building on (Chli and Winsper, 2015), it ensures incentive compatibility while integrating trust and reputation to minimise risk and maintain service quality.
Knowledge Transfer Partnership with RL Capital Ltd
Innovate UK
2020-2023
Building on our work in transfer for reinforcement learning (Carr et al., 2019), funded a postdoctoral associate to develop a real-time wheel alignment fault detection system, improving accuracy to reduce fuel use, emissions, and tire wear.
Knowledge Transfer Partnership with Agilysis Ltd
Innovate UK
2022-2025
Funding a postdoctoral associate to work on developing a predictive air quality model for transport planning. This project is a result of our work on traffic modelling and control (Garg et al, 2018-2022).
EPSRC Impact Acceleration Award
UKRI & Coventry City Council
Deployment of our AI signal control system on two junctions at Coventry, in addition to impact maximisation and outreach activities. This is one of the very few AI traffic trials ever conducted.
Knowledge Transfer Partnership with Smart Transport Hub
Innovate UK
2024-2027
The project aims to create an innovative in-vehicle monitoring solution that utilises and machine learning to capture and analyse road conditions and infrastructure. This builds upon our traffic control (Garg et al. 2018-2022) and urban simulation work (Garg et al, 2019 and Criado et al, 2023) which is being deployed at Coventry City Council, this project is also expected to deliver substantial impact through stakeholder adoption.
Knowledge Transfer Partnership with Aurrigo
Innovate UK
2025-2028
To develop a dynamic, optimised efficiency software platform to transition Aurrigo's fleet management for airport baggage/cargo-handling autonomous vehicles from centralised, human-control to a decentralised, autonomous command-and-control system
National Evaluation of the Healthy Start Scheme UK
NIHR
2026-2028
To develop a participatory agent-based model (ABM) to simulate how families, local systems, and policy choices interact to drive uptake of Healthy Start vitamins and financial support, capturing real-world local variation. Co-created with families, practitioners and policymakers, the ABM will integrate qualitative insights, supply-chain mapping and economic evidence to test reform scenarios before implementation. This will enable local and national decision-makers to predict uptake, costs and impacts of alternative Healthy Start reforms, strengthening evidence-based policy design.
Articles
Optimal Auction Design for the Gradual Procurement of Strategic Service Provider Agents
arXiv preprint2021
We consider an outsourcing problem where a software agent procures multiple services from providers with uncertain reliabilities to complete a computational task before a strict deadline. The service consumer requires a procurement strategy that achieves the optimal balance between success probability and invocation cost. However, the service providers are self-interested and may misrepresent their private cost information if it benefits them. For such settings, we design a novel procurement auction that provides the consumer with the highest possible revenue, while giving sufficient incentives to providers to tell the truth about their costs. This auction creates a contingent plan for gradual service procurement that suggests recruiting a new provider only when the success probability of the already hired providers drops below a time-dependent threshold. To make this auction incentive compatible, we propose a novel weighted threshold payment scheme which pays the minimum among all truthful mechanisms. Using the weighted payment scheme, we also design a low-complexity near-optimal auction that reduces the computational complexity of the optimal mechanism by 99% with only marginal performance loss (less than 1%). We demonstrate the effectiveness and strength of our proposed auctions through both game theoretical and numerical analysis. The experiment results confirm that the proposed auctions exhibit 59% improvement in performance over the current state-of-the-art, by increasing success probability up to 79% and reducing invocation cost by up to 11%.
Traffic3d: An Open-Source Traffic-Based Interactive Framework to Train AI Agents
SSRN2022
Significant breakthrough in the field of artificial intelligence (AI) has been driven by the use of game environments for training and evaluating autonomous agents. Inspired by the extensive literature on the use of game-based simulation environments, in this paper, we present a novel edition of a 3D-road traffic environment; Traffic3D. Traffic3D is a rich, realistic and extensible simulation platform built to reproduce real-world dynamic and diverse traffic scenarios; incorporating adequate physical behavior and life-like visual appearance of the traffic entities (such as vehicles and transportation infrastructure) as well as environment and road conditions. A seamless interface with python makes it possible to use Traffic3D, not only as a simulator but as a rich training ground for AI-powered autonomous traffic tasks, such as autonomous driving and traffic signal infrastructure optimization. To showcase Traffic3D's capabilities in producing real-world deployable AI agents, we trained an AI agent to achieve fully-autonomous signal control by effectively regulating the traffic flows through the road intersections in {\em real time} based {\em solely} on {\em live} traffic footage. Our empirical analysis demonstrates that our agent while being entirely trained in simulation transfers seamlessly to the real world and reliably adapts to novel traffic situations. To support the research community in the development of new techniques,we have made Traffic3D publicly available at https://traffic3d.org.
Fully-Autonomous, Vision-based Traffic Signal Control: from Simulation to Reality
ACM2022
Ineffective traffic signal control is one of the major causes of congestion in urban road networks. Dynamically changing traffic conditions and live traffic state estimation are fundamental challenges that limit the ability of the existing signal infrastructure in rendering individualized signal control in real-time. We use deep reinforcement learning (DRL) to address these challenges. Due to economic and safety constraints associated training such agents in the real world, a practical approach is to do so in simulation before deployment. Domain randomisation is an effective technique for bridging the reality gap and ensuring effective transfer of simulation-trained agents to the real world. In this paper, we develop a fully-autonomous, vision-based DRL agent that achieve adaptive signal control in the face of complex, imprecise, and dynamic traffic environments. Our agent uses live visual data (i.e. a stream of real-time RGB footage) from an intersection to extensively perceive and subsequently act upon the traffic environment. Employing domain randomisation, we examine our agent’s generalisation capabilities under varying traffic conditions in both the simulation and the real-world environments. In a diverse validation set independent of training data, our traffic control agent reliably adapted to novel traffic situations and demonstrated a positive transfer to previously unseen real intersections despite being trained entirely in simulation.
