Research Associate in Swarm Robotics

Overview

The University of Sheffield is a remarkable place to work. Our people are at the heart of everything we do. Their diverse backgrounds, abilities and beliefs make Sheffield a world‑class university.

We offer a fantastic range of benefits including a highly competitive annual leave entitlement (with the ability to purchase more), a generous pension scheme, flexible working opportunities, a commitment to your development and wellbeing, a wide range of retail discounts, and much more.

We are seeking an experienced researcher to lead the development of decentralised swarm mapping and localisation algorithms for underground pipe operations as part of an international research programme funded by the Engineering and Physical Sciences Research Council (EPSRC). The programme is developing machine intelligence for teams of autonomous robots working in buried water infrastructure.

You will lead the design of methods that enable robot swarms to explore pipe networks, share information, support anomaly detection, and coordinate reporting and dispatch decisions in environments with limited communication, sensing and power. The role also includes validating these methods through simulations and physical robot experiments. The development of uncertainty aware methods, such as Gaussian processes with learning capabilities is essential, including data association and other Bayesian methods.

You will join a collaborative research environment at the University of Sheffield, working across the School of Electrical and Electronic Engineering, Centre for Machine Intelligence and Sheffield Robotics with international partners including TU Darmstadt, MIT and Boston University. There is an opportunity for extensive international travel to work closely with our overseas partners and to present research to peers at key international conferences.

You will help translate ambitious ideas into robust algorithms and convincing experimental demonstrations. You will also contribute to the strategic direction of this research area, support publications and project coordination, and help develop future funding applications and collaboration opportunities.

We are looking for someone with a PhD in robotics, computer science, control, AI or a closely related field, and a strong background in swarm robotics, multi‑robot systems or distributed autonomous systems. You should be able to work with a high degree of independence, contribute to collaborative leadership, and develop innovative solutions to technically challenging problems.

• Lead the development of novel decentralised swarm algorithms for mapping in underground pipe operations, with particular focus on exploration, collective decision‑making, information sharing, reporting and robot navigation.
• Develop sensor data fusion algorithms that are an essential element of the joint robot mapping tasks in the presence of data origin uncertainties. Knowledge of Bayesian approaches such as Gaussian process regression, particle filters, Bayesian networks, graph‑based approaches. Probabilistic‑based uncertainty quantification is also essential.
• Lead the design, implementation and evaluation of bio‑inspired, optimisation‑based and machine‑learning‑enabled methods that enable robot teams to operate under constraints on communication, sensing, computation and power.
• Lead the development and maintenance of high‑quality research software for simulation, computer vision‑based algorithms (with optical videos, Lidar and other data), testing and deployment on robotic platforms, using reproducible and well‑documented development practices.
• Develop centralised and decentralised algorithms for the swarm of robots performing underground inspections.
• Lead the planning and delivery of simulation studies and laboratory experiments to validate swarm algorithms, including coordinating their integration with related mapping, sensing and robotic platform activities across the wider programme.
• Lead the analysis and interpretation of simulation and experimental data, using the findings to direct method refinement and inform project priorities, research decisions and longer‑term…