Skip to main content
School of Electronic Engineering and Computer Science
  1. School of Electronic Engineering and Computer Science
  2. PhD
  3. PhD studentships
  4. Modelling Cyclist Safety Perception and Behaviour Using Agent-Based Simulations

Modelling Cyclist Safety Perception and Behaviour Using Agent-Based Simulations

Modelling Cyclist Safety Perception and Behaviour Using Agent-Based Simulations 

Supervisors: Mona Jaber and Richard Clegg 

Project Description 

Active travel, including walking and cycling, is vital for the environment and public health but levels of cycling remain well below expectations. Good models of cyclist behaviour and interaction with the environment can genuinely help urban planners to better support cyclists’ priorities. This project will focus on improving how models capture cyclist behaviour in the real world. Cyclist behaviour is influenced by many things including their perception of how safe routes are, the types of infrastructure they like to use (dedicated cycle lanes versus roads that may be faster) and their willingness to share the road with cars. Different cyclists may have vastly different preferences: an impatient cyclist who tolerates risk might avoid a cycle lane shared with slower cyclists while a risk averse cyclists might tolerate the delay for a safer journey. This project will develop agents that can capture this diversity. These agents will be integrated into an agent-based simulation tool to model counterfactual cycling and urban planning scenarios to support decision making. 

This PhD research aims to develop and validate a safety-aware digital twin framework with the following specific objectives: 

Primary Objective: Design and implement a machine learning approach that transforms real-world cyclist observations into representative behavioural agents for transport simulation tools, enabling more reliable evaluation of cycling infrastructure, route choices, and interventions supporting sustainable urban mobility. 

Secondary Objectives: 

  1. Based on existing data, apply explainable AI and fusion of data obtained from different sensors (e.g., camera and inertial measurement unit) to identify relationships between cyclists’ perception of safety, infrastructure characteristics, traffic conditions, and their behaviour. 
  1. Develop empirically grounded cyclist personas; these are representative behavioural profiles, that captures the characteristics, preferences, perceptions and decision-making tendencies of a particular group of cyclists. 
  1. Integrate cyclist personas into a agent-based simulator (e.g., MATsim.org) and validate their ability to reproduce observed mobility patterns. 
  1. In the simulation environment, investigate geographical transferability and the implications of infrastructure interventions on cyclists’ trends. 

Prerequisites:  

Essential: 

  • A bachelor’s degree in computer science, artificial intelligence, data science, electrical and electronic engineering or a closely related discipline. 
  • Solid understanding of machine learning and data analytics. 
  • A keen interest in developing and evaluating Agent-Based Simulations 

Desirable:  

  • Master’s degree (with distinction or equivalent) in computer science, artificial intelligence, data science, electrical and electronic engineering or a closely related discipline. 
  • Experience with Intelligent Transportation Systems  

 The PhD studentship is funded by EPSRC Doctoral Landscape Award open to those with Home and International fee status. However, the number of students with international fee status who can be recruited is capped according to the EPSRC terms and conditions, so competition for international places is particularly strong. Awards are tenable for up to 3.5 years, and cover tuition fees and a maintenance stipend at the UKRI rate (c. £23,805 p.a. full-time, £11,902.50 part-time for 2026/27; and 2027/28 rates tbc). 

 How to apply: 

 Queen Mary is interested in developing the next generation of outstanding researchers and decided to invest in specific research areas. 

 Applicants should work with their prospective supervisor and submit their application following the instructions at: http://eecs.qmul.ac.uk/phd/how-to-apply/.   

 The application should include the following:  

  • - CV (max 2 pages)   
  •  Research proposal (max 500 words)  
  • - 2 References   
  • - Certificate of English Language (for students whose first language is not English)   
  • - Other Certificates   

Please note that in order to qualify as a home student for the purpose of the scholarships, a student must have no restrictions on how long they can stay in the UK and have been ordinarily resident in the UK for at least 3 years prior to the start of the studentship. For more information please see: (https://epsrc.ukri.org/skills/students/guidance-on-epsrc-studentships/eligibility)   

Application Deadline: The deadline for applications is  16:00 GMT , 27th January 2027.   

For specific enquiries contact Dr Mona Jaber at m.jaber@qmul.ac.uk.  

For general enquiries contact eecs-phd-enquiries@qmul.ac.uk with the subject “EECS 2027 PhD scholarships enquiry”. 

 

Back to top