[School of Engineering PhD Scholarships] Minimalist Autonomy: Safe and Sustainable Neurosymbolic Systems

About the project

About the Project Autonomous systems need to make decisions in complex, uncertain, and changing environments. Machine learning, generative AI, and foundation models offer strong capabilities but can be expensive, unpredictable, unsustainable, and unsuitable for decisions that require strong guarantees. Classic algorithms and symbolic methods provide transparency and verifiability, but may lack flexibility in unfamiliar situations. This PhD project asks how much learnt autonomy (aka neural AI) a system requires. Particularly, should we begin with the simplest verifiable solution and introduce learnt components only when improvements in capability justify the risk and cost? Should we use learnt AI models, or use them to design transparent, verifiable symbolic algorithms for autonomous systems?... The aim is to establish frameworks for verified minimalist autonomy. Minimalism preserves capability while avoiding unnecessary complexity, opacity, and resource consumption. Neurosymbolic frameworks allocate responsibility among learnt components, symbolic reasoners, conventional algorithms, and human supervisors. At each decision point, the system will select the least complex mechanism capable of meeting its requirements, while ensuring the entire system remains verifiable and safe. Possible research directions include: Minimal neurosymbolic architectures: Determining the smallest combination of learnt/neural components required to achieve a specified mission. Risk-aware escalation: Using uncertainty quantification and statistical calibration to determine when computation, a more capable model, or human intervention is justified. Runtime assurance: Creating monitors, shields, fallback mechanisms, and safe-degradation strategies for systems operating beyond their validated operating envelope. Economic viability: Accounting for computation, latency, energy, assurance, supervision, and failure costs, and evaluating when symbolic, learnt, or hybrid approaches provide the strongest overall case. The project will apply these ideas to representative case studies in robotics, decision support, and software agents, producing methods and evidence for autonomy that is sufficient, verifiable, and sustainable. This project is expected to start in September 2027. Before you apply: We strongly recommend that you contact the supervisors for this project before you apply. How to apply: To be considered for this project you must complete a formal application through our online application portal. If you already have an applicant account this link will directly open an application for PhD School of Engineering Scholarships . If you don’t already have an applicant account, please follow the instructions here. . When applying, please specify the full title and supervisor/s of the project, details of your previous study, and names and contact details of two referees. You must also upload a Supporting Statement describing the motivation to apply to the project, your CV and transcripts of awarded and in-progress university qualifications . Please note late or incomplete applications will not be considered. Equality, diversity and inclusion are fundamental to the success of The University of Manchester and central to all our activities. A diverse research community strengthens creativity, productivity and quality, while increasing the societal and economic impact of our work. We welcome applicants from all career paths, backgrounds and sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation or transgender status. We welcome applications from candidates returning to study after a career break or experience in other roles. Flexible study arrangements may be available, including part-time study at 50%, 60% or 80%, subject to the requirements of the project and funder. Eligibility : The standard academic entry requirement for this PhD is an upper second-class (2:1) honours degree in a discipline directly relevant to the PhD Computer Science, Mathematics, or Engineering (or international equivalent) OR any upper-second class (2:1) honours degree and a Master’s degree at merit in a discipline directly relevant to the PhD Computer Science, Mathematics, or Engineering (or international equivalent). This project will remain open until filled. If your application is submitted by 1 st November 2026, you can expect a decision by 18 th December 2026. If your application is submitted by 15 th January 2027, you can expect a decision by 30 th March 2027. Self or externally funded students can also be considered for this project. FSESoE

Research areas