Towards Energy Efficient Autonomous Vehicles via Cloud-Aided Learning

There are two ongoing revolutions in modern automotive industry. The first is the development of autonomous transportation systems which is leading to greatly improved safety, traffic economy, environment and passenger comfort. The second on is the development of advanced propulsion systems, envisaging reduced fuel consumption and exhaust emissions. The intersection of the autonomous transportation systems and advanced propulsion systems is the future trend, which has been revealed in the strategic partnerships between automakers and IT companies. However, there is a big challenge that the environment information collected by autonomous vehicles is poorly used in propulsion systems, especially when vehicles run in fast changing conditions. Only few examples of using environment data to optimise energy efficiency can be found, although the potential benefits in fuel reduction and mission flexibility are great.

This project aims to tackle this challenge by developing a cloud-aided learning framework to merge the two themes as integrity. To establish awareness of the environment, the onboard sensors of autonomous vehicles including cameras, light detecting and ranging (LiDAR), ultrasonic, and radar are used to perceive the environment over short distances. The GPS and intelligent transportation systems are used to perceive the environment at a further distance. The combined information enables the autonomous vehicle to establish a comprehensive model of the external environment. Using advanced machine learning algorithms (e.g., dynamic Bayesian network), the environment information can be used to update the propulsion system model in real time. Combining the real-time updated model with dynamic optimisation methods (e.g., adaptive model predictive control), the optimal actions of the propulsion system can be obtained in s systematic way. Employing high performance computing resources on cloud, the computational intensive modelling and optimisation tasks can be cost-effectively addressed.

Aligning with the EPSRC Innovation Fellowship priority area of "Robotics and Artificial Intelligence Systems" through its focus on efficient transport, a cloud-in-the-loop testing platform will be built. This framework focuses on sensing, modelling, control, optimisation and computing of energy efficient autonomous vehicles. In a long term vision, the framework can be generalised from a single vehicle to connected and autonomous for further economic benefits.

This research will address several fundamental problems in developing future vehicle architecture, from both theoretical and application aspects. Finding a way to successfully utilise external information will break down a wall that currently exists between research in autonomous driving and engine control and, therefore, an energy efficient autonomous vehicle can be delivered. This research has considerable potential economic benefit. It embraces the driverless technology market worth up to £50 billion to the UK economy by 2035. Also, it anticipates the government's clean energy policy on low carbon vehicles up to 2040. Future developments in the UK automotive industry, including technical innovations and competitive advantages, will be greatly aided by this research that will provide a bridge between laboratory models and production vehicles. To make this happen, I will focus on the following dissemination and impact activities.

Advisory board meetings composed by both academia and industry will be organised to engage with partners from the start, ensuring a close and fruitful collaboration. The advisory board will lead to two-way conversations between academia and industry, allowing me to will act as an ambassador for research and innovation across interfaces.

A website hosted by LU will be established to increase visibility. Links to the publications, testing videos, tutorial example and a part of algorithm codes would be made available. Similar information would also be published on my homepage. LinkedIn and ResearchGate will also be used to disseminate the research outcomes.

The research outcomes will be presented in industrial workshops and exhibitions including the Future Powertrain Exhibitions and the Consumer Electronics Show. The attendance will attract the interest of many suppliers from decision-making industry and data industry. Also they are ideal opportunities to ensure the technology being generalised.

Working with the host organisation and industrial partners, I will apply for international patents throughout the project.

I will give free webinars through the platform provided by IEEE and Mathworks. The latest research findings would be presented to public through the "IEEE Tech Insider Webinars" and the "Matlab and Simulink Webinars for Academia". Public lectures will be given at Open Days and Student Visits at LU. I will also become a STEM ambassador to disseminate ideas by initiating an activity through the STEM ambassador hubs.

High quality papers will be published in top tier IEEE journals. The research outcomes be also submitted to the most prestigious conferences including IEEE Conference on Decision and Control and International Conference on Robotics and Automation and SAE Congress. The publications will be made open access and shared via the open LU Publications Information Login (LUPIN) system.

Prototype testing will be given in Smart Mobility Living Lab facility, London and the engagement with common end users and media will be emphasised.

I will give consultations to Department for Transportation (DfT) of UK for the policy making of vehicles manufacturing transportation infrastructure in the future. I will work closely with Prof Ricardo Martinez-Botas, a science advisory council member of DfT, to offer the technical support.

AI will organise a workshop to disseminate the results to representatives from industrial partners in LU. I will invite established partners with whom I have connections and potential partners to join the industrial workshop. By successful demos, this pioneering work can build the confidence of automakers and attract more industrial partners.