Back to search results

PhD Position in Realistic Automotive Sensor Models

University of Warwick - WMG

Qualification Type: PhD
Location: Coventry
Funding for: UK Students, EU Students, International Students
Funding amount: £15,009 per annum
Hours: Full Time
Placed On: 17th October 2019
Expires: 16th January 2020

Supervisor name: Mehrdad Dianati

Start date: ASAP

Closing date: 31st July 2019

Project Overview

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.

  • An understanding of and experience in using virtual simulation tools for development and test.
  • Familiarity with machine learning and probabilistic models, preferably including generative models.
  • Relevant software knowledge and experience, for example Python and tensor frameworks (PyTorch or TensorFlow), C++, etc.
  • Analytical and numerical skills.
  • Ability to define and build experiments and analyse data.
  • A driven, professional and independent work attitude.
  • Ability to liaise with academic supervisors from a range of disciplines.
  • Excellent written and verbal communication skills.

To apply: Please visit the WMG website directly to apply for this studentship:

We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

Subject Area(s):


PhD tools
More PhDs from University of Warwick

Show all PhDs for this organisation …

More PhDs like this
Join in and follow us

Browser Upgrade Recommended has been optimised for the latest browsers.

For the best user experience, we recommend viewing on one of the following:

Google Chrome Firefox Microsoft Edge