AI optimisation via robust and sustainable fusion of perception sensors’ data in Intelligent Vehicles.

About the Project

Automated Systems in the field of intelligent transportation (from vehicles to drones and beyond) have made significant progress in the last 10 years, for example reaching the level of services like ‘Robot-taxis’ by Waymo, Cruise, Pony.ai in different countries. However, these services are limited in their deployment, particularly due to the inherent noise and situational complexity in the driving environment, that affects data collection by sensors like cameras, LiDARs, 4D RADAR, etc. Degraded sensors’ data can affect the Artificial Intelligence (AI) algorithms and deep neural networks using this data, affecting the safety of the entire automated systems and other road stakeholders. This project aims to be a stepping stone in the safety of future automated vehicles, developing effective ways to combine perception sensors data, and considering the trade-offs between robustness, data amount, and energy consumption.

Some of the potential activities you will have to carry out to achieve this aim will be:

• understanding how perception sensors data degrades in the real world, considering techniques of data augmentation if needed;
• understanding how to reliably measure data quality for different sensor modalities;
• understanding how to effectively and real-time use AI to combine data, leveraging information on data quality and foreseeing potential risks in the environment.

Research Team and Facilities

You will be part of Sensing and Perception for Intelligent Systems (SPRING) Group, part of the Advanced Robotics Centre (ARQ) and the Centre for Intelligent Transport research group and work with several enthusiastic and passionate researchers that will support you to develop your knowledge and skills related to the project and the wider research field. The SPRING group is a world leading group specialised in perception sensors for automotive, sensors’ data collection and modelling, AI for perception, safety and testing. We have been contributing to international projects such as the EU Horizon ROADVIEW, tackling Robust Sensing in adverse weather, and we have numerous industrial and academic partners across Europe and beyond. You will leverage this network to develop as a researcher with a strong portfolio, ensuring that your contribution to new knowledge can shape the future in the field of automotive and automated systems.

Who are we looking for?

• Applicants should hold/achieve a master’s degree (or international equivalent) in an engineering discipline, physics, computer science, mathematics, or similar. Applicants without a master's qualification may be considered on an exceptional basis, provided they hold a first-class undergraduate degree.
• Strong interest and enthusiasm in sensing, perception, and AI techniques.
• Proactive attitude, excellent communication and teamwork skills.

Funded by: EPSRC

Stipend is the UKRI rate of £23,805 p.a.

Eligibility

• The minimum requirement for this studentship opportunity is a good honours degree (minimum 2(i) honours or equivalent) or MSc/MRes in a relevant discipline.
• If English is not your first language, you will require a valid English certificate equivalent to IELTS 6.5+ overall with a minimum score of minimum score of 6.0 in each of Writing, Listening, Reading and Speaking).
• Note for EPSRC studentships; these studentships are open to those with Home and International fee status; however, the number of students with International fee status which can be recruited is capped according to the EPSRC terms and conditions so competition for International places is particularly strong.

Funding Notes

Funded by: EPSRC

Stipend is the UKRI rate of £23,805 p.a. fpr Home fees students.