PhD Studentship: Multi-sensor Fusion for Robust Reinforcement Learning in Uncertain Environments

Coventry University

In many real-world applications, relying on a single sensor can be problematic due to noise, occlusions, or other various uncertainties. Using data from multiple sensors can improve the decision-making process. Reinforcement Learning (RL), as one of the three major machine learning approaches together with supervised and unsupervised learning, has found a lot of applications in control and robotics in recent years. The overall aim of this project is to enhance the performance and robustness of RL agents by fusing data from multiple sensor modalities. This will involve the development of an RL framework that integrates data from multiple sensors (e.g., cameras, LiDAR, ultrasonic, infrared) to form a unified state representation. The agent will learn to weigh the reliability of each sensor’s data based on the current context. It is expected that the project will produce real-world impact by developing RL agents that can operate effectively even when some sensors are compromised or when operating in challenging and uncertain environmental conditions.

The successful applicant will start with developing a solution that can work in a simulated environment and then gradually include additional real-world aspects. It is expected that, throughout the PhD programme, the applicant will be interacting and collaborating with the industry contacts to ensure that the approach meets their needs. The final goal is to provide the industry with a solution that can be brought to market and used within robotics and other sensor-based applications.

Entry criteria for applicants to PhD

  • A bachelor’s (honours) degree in a relevant discipline/subject area with a minimum classification of 2:1 and a minimum mark of 60% in the project element (or equivalent), or an equivalent award from an overseas institution.


  • the potential to engage in innovative research and to complete the PhD within 3.5 years
  • An adequate proficiency in English must be demonstrated by applicants whose first language is not English. The general requirement is a minimum overall IELTS Academic score of 7.0 with a minimum of 6.5 in each of the four sections, or the TOEFL iBT test with a minimum overall score of 95 with a minimum of 21 in each of the four sections.

For further details please visit:

The applicant is not required to submit a research proposal as part of their application. Within the supporting statement, candidates should articulate why they believe they are suited for this position. Specifically, we anticipate that the applicant will demonstrate some experience/and or knowledge pertinent to machine learning and will have good programming skills.

To find out more about the project please contact Prof. James Brusey at [email protected]

All applications require a covering letter and a 2000-word supporting statement is required showing how the applicant’s expertise and interests are relevant to the project.  

View or Apply
To help us track our recruitment effort, please indicate in your cover/motivation letter where ( you saw this job posting.

Job Location