Institute for Future Transport and Cities

Email: ugwuezeo@coventry.ac.uk

This project will develop novel, next-generation additive manufacturing to integrate thermoelectric generators and heat management systems into a single-piece structural part to optimise energy harvesting from hot pipes; vastly improving structural integrity, heat-exchanger leak-tightness, and component compactness and efficiency.

How can AI be utilised and implemented to provide safer and more effective self-driving vehicles? This PhD will focus on the adequate service and the level of safety for both the users and its environment to be deemed effective. 

Currently, one of the main problems is modelling the LIDAR sensor. Modelling automotive LIDAR is complicated by effects such as multipath reflections, interference, reflective surfaces, discrete cells, and attenuation. Detailed LIDAR simulations based on physical principles exist but are computationally expensive for realistic automotive scenes. Furthermore, they depend on some physical parameters that are unknown and need to be identified. This PhD project will investigate a methodology for the construction of data-based automotive LIDAR models based on deep learning.

When plants are stressed, at the molecular level, their complex network of genetic components are altered, resulting in suboptimal biological functions. From the viewpoint of control engineering, stress response mechanism can be naturally formulated as a disturbance rejection problem and the goal is to utilise the systems theory components (e.g. network science, systems biology, control theory) to develop tools for designing synthetic genetic controller to improve stress responses mechanism in plant. Student will carried out analyses include network modelling, theoretical analysis, control design and simulation that seek to engineering resilient plants under stress.