Department of Engineering

A substantial amount of underground construction, much of it in urban environments, is planned in the UK for the coming decades. This includes major projects such as High Speed 2 (estimated £107 billion) as well as transport upgrade projects such as the Bakerloo Extension (£2.57 billion). Given the current economic climate and the UK's current progress on the Net-Zero agenda, we urgently need new ways to deliver this infrastructure in a way that is low-cost, efficient and sustainable. In partnership with start-up hyperTunnel Ltd, University of Cambridge will deliver a key enabler, namely underground digital twins, of future tunnelling operations to alleviate these pain points.

Future underground infrastructure will be built by autonomous swarming robots. The robots will (a) survey the ground, (b) feed live data to a digital twin of the tunnel to update and optimise construction operations by the swarm, and (c) inform engineers of progress. The aim of this PhD research is to achieve a step-change in how underground digital twins are constructed by leveraging recent advances in sensor data fusion and machine learning (ML). Digital ground surveying techniques (e.g. ground penetrating radars, seismic scanner, camera and Lidar) will be used to develop 3D mapping of the underground space during construction. A scalable ML framework will be developed to achieve accurate 3D reconstruction and perform perception, prediction and planning tasks. The fused sensory inputs will subsequently be used to build the digital twin. The developed framework will be developed and validated through real-world data provided by industry partner and infraTech start-up hyperTunnel Ltd. The project is co-funded by hyperTunnel Ltd and will be supervised by Dr Brian Sheil.

https://www.jobs.cam.ac.uk/job/38714/