Edge-to-Cloud Smart Mobility: AI Co-optimization for Future Autonomous Vehicles

Summary

Are you excited to contribute to a future of safe autonomous self-driving cars? Or are you fascinated to study the impact of autonomous vehicles mobility on cutting-edge computing infrastructures such as the edge-to-cloud continuum? This project is a unique opportunity to make both happen!

Vision: Imagine yourself as a creator of a highly versatile coupled infrastructure of computing and vehicles, where computing ‘follows’ vehicles, and vehicles ‘follow’ computing! An infrastructure that is resilient, secure and self-adaptive to unanticipated changes, putting the foundations for meeting ambitious net zero targets!

Methods and aim: Using advanced distributed Artificial Intelligence (AI) and optimization methods such as reinforcement, federated and collective learning, you will introduce techniques to load-balance the computational load within the edge-to-cloud continuum, as generated by new emerging mobility patterns of autonomous vehicles. With this load-balancing, passengers will experience higher safety and quality of services, such as augmented reality, by optimizing for lower latency, lower service violations and higher throughputs. Complementary, you will be introducing vehicle rerouting techniques that will prioritize for routes that do not overload computing infrastructures during computational offloading to preserve safety and quality of service. Ultimately, you will aim to unravel the interplay of these two coupled co-optimization processes and understand how to coordinate distributed resources for computing resources and transport systems.

Opportunities for impact: This project provides unprecedented opportunities to make a PhD with impact on society. With well-established industrial collaborators, partnerships with policy makers and urban traffic control systems of cities and a large network of international collaboration partners, you will be in the strongest position to bring research in real-world, work with real-world data, and explore different prominent career development pathways.

Team and supervision: This project also provides the opportunity to make your PhD with fun, by being integrated and supported within a creative, diverse and inclusive team of talented students and research fellows working on ambitious research projects such as a UKRI Future Leaders Fellowship. You will have strong supervision support by two experts in this area. This includes regular meetings, a tailored development plan, mentorship and coaching to deal with every challenge you will encounter during your PhD.

This project will benefit from the following skills and knowledge: Solid software programming skills: Python, C, C++ or Java, UNIX and scripting skills, Strong knowledge of statistics, Knowledge of the foundations of distributed systems and AI.

Future smart mobility will include autonomous, shared and electric vehicles and the need to shift to low-transport carbon modalities to tackle climate change. However, existing information and communication technologies such as cloud computing cannot meet the requirements of this ambitious transition. This PhD project aims to create a self-adaptive infrastructure for smart mobility that will harvest computational resources within the edge-to-cloud continuum using distributed artificial intelligence and optimization methods such as reinforcement, federated and collective learning. As a PhD candidate in this project, you will be part of a creative and diverse team with excellent supervision, while you will collaborate with high-profile industrial partners that will unravel future career development opportunities and access to state-of-the-art technologies.

References

1. Nezami, Z., Pournaras, E., Borzouie, A. and Xu, J., 2023. SMOTEC: An Edge Computing Testbed for Adaptive Smart Mobility Experimentation. arXiv preprint arXiv:2307.11181.
2. Nezami, Z., Zamanifar, K., Djemame, K. and Pournaras, E., 2021. Decentralized edge-to-cloud load balancing: Service placement for the Internet of Things. IEEE Access, 9, pp.64983-65000.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.5 overall with at least 6.5 in writing and at least 6.0 in reading, listening and speaking or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.