|Funding for:||UK Students, EU Students, International Students|
|Funding amount:||£15,009 per annum|
|Placed On:||17th October 2019|
|Expires:||16th January 2020|
Supervisor name: Mehrdad Dianati
Start date: ASAP
Closing date: 31st July 2019
This PhD will focus on the investigation and development of realistic automotive sensor models to support autonomous control functions/systems development, test and validation. This is a challenging and unique PhD opportunity for a student with a background in machine learning, probabilistic models, sensor simulations and an interest in applying their knowledge in the rapidly growing area of connected autonomous vehicles.
Rich simulated virtual environments are increasingly being used to support research and development of autonomous control functions from the early stages of the development cycle. Simulated virtual environments are also widely accepted to play a vital role in autonomous control function validation and verification testing - given their complexity and vast number of possible inputs that would make it impractical to purely test in the physical world. On-vehicle and infrastructure sensors (i.e. LIDAR, radar and camera) form the core inputs to the functions (perception, path planning and decision making) that make up an autonomous vehicle. Accurate and reliable sensor data is therefore critical in testing and evaluating the behaviour and performance of these functions.
Current simulation software packages that are available on the market lack realistic sensor models (particularly LIDAR, but also RADAR, Ultrasonic and camera). For example, most software packages provide only idealistic range data for each LiDAR beam. Without consideration of optical beam properties, material properties, weather conditions and interference from other sources. This limits the overall value offered by simulation software during development and test.
This PhD will explore methods to significantly improve existing sensor models and to create novel realistic sensor models to support automotive applications. The project will look to use novel tools and techniques such as computer simulation and machine learning to develop sensor models that are more realistic and representative in behaviour and performance as their physical counterparts.
Funding Source: WMG Funded
Funding Duration: 3 years
Stipend: Standard Research Council Maintenance Award - £14,777
Funding Eligibility: International, Home/EU applicants
Desired Student background:
We are seeking an enthusiastic individual to join the Intelligent Vehicles research group at WMG, University of Warwick with the following attributes:
A minimum 2.1 undergraduate (BEng, MEng) and/or postgraduate masters’ qualification (MSc) in a science and technology field: Engineering, Mathematics, and Computer Science.
To apply: Please visit the WMG website directly to apply for this studentship:
Type / Role: