The project aims to explore the active safety potential of artificial intelligence (AI) algorithms for the control of multiple chassis actuators (electric powertrains, brake-by-wire, four-wheel-steering and active suspension) in automated vehicles operating at and beyond the limit handling.
Studentship group name
Autonomous Robotics and Vehicles
School of Mechanical Engineering Sciences
For the first time in the literature, this project will systematically assess the active safety potential of AI-based integrated chassis control for automated vehicles operating at and beyond the limit of handling. The case study will be represented by automated vehicles with multiple chassis actuators, e.g., individually controlled electric powertrains, active suspension systems, four-wheel-steering, brake-by-wire, and active suspension kinematics. The activity will focus on the development and evaluation of integrated chassis control architectures with AI-based supervisory layers, neural network model predictive controllers, as well as deep reinforcement learning algorithms. The benefits will be assessed in terms of vehicle dynamics and active safety performance, robustness with respect to the variation of vehicle parameters, computational efficiency, and reduction in the state estimation requirements.
The AI-based algorithms of this PhD project will also enable the implementation of dedicated stability control paradigms for automated vehicles. In fact, the state-of-the-art vehicle stability controllers intervene during emergency manoeuvring by restricting the response of the vehicle within a stable regime of low wheel slip and vehicle sideslip angle – i.e., operating conditions that are predictable and more easily controllable. The driver or automated driving system maintains the responsibility of providing the necessary actions to avoid an accident, relieved from the challenge of controlling the vehicle in unstable and non-intuitive operating conditions. However, this approach does not always make use of the true capabilities of a vehicle. Previous research on specialised driving techniques used by expert human (race) drivers has demonstrated quantifiable performance benefits from vehicle operation in extreme conditions with high wheel slip and vehicle sideslip angle. For example, trail braking and power-oversteer techniques are used to achieve higher speed in tight (low radius) corners. The paradigm of active safety systems, which restrict the response of the vehicle to make it predictable and intuitive for the average human driver, becomes a rather conservative proposition in the context of automated vehicles, which could benefit from the implementation of extreme driving techniques in emergency scenarios, through AI-based algorithms.
The candidates should apply online to the Automotive Engineering PhD programme, and they are encouraged to contact Professor Aldo Sorniotti ([Email Address Removed]) before submitting their applications.
How to Apply
Open to UK and International students starting in October 2023.
Applications should be submitted via the Automotive Engineering PhD programme page. In place of a research proposal you should upload a document stating the title of the projects (up to 2) that you wish to apply for and the name(s) of the relevant supervisor. You must upload your full CV and any transcripts of previous academic qualifications. You should enter ’Faculty Funded Competition’ under funding type.
The studentship will provide a stipend at UKRI rates (currently £17,668 for 2022/23) and tuition fees for 3.5 years. An additional bursary of £1700 per annum for the duration of the studentship will be offered to exceptional candidates.