facebook tracking

Master Thesis - driving profile identification using machine learning

Background

An important challenge to release autonomous vehicles to public roads is the safety verification. In order to be able to argue for safety of autonomous driving, a verification machinery will have to combine several evaluation tools such as road testing, scenario-based testing using simulation environment, etc. The scenario-based testing aims to combine and/or extrapolate the identified scenarios from road testing to find a set of scenarios, or so-called test cases, which can expose the AD vehicle to safety critical situations. 

The important factors that influence the extracted scenarios are the environment, surrounding traffic, and the driver behavior. It is profoundly important to address the impact of the driving style of drivers during road testing on the dynamics of the traffic scenarios which they are exposed to.

Project Description

The aim of this master thesis is to study the impact of the driving style on the extracted scenarios from road testing. The student will be provided with a tagged database of real-world driving scenarios from about hundreds of thousand kilometers of road testing. The idea is to try various state-of-the-art machine learning techniques such as Bayesian Networks to segment the time series driving dataset to a set of fundamental driving patterns without a prior knowledge of the number of these patterns. 

The extracted fundamental driving patterns are then clustered and semantically labeled according to driver’s features. Based on this, information-theoretic metrics will be used to perform a driving style analysis.

Qualifications

We are looking for a student with the following skills:

  • creative mindset
  • strong background in mathematics, statistical modelling, machine learning and deep learning
  • solid programming skills like Matlab and Python
  • passion for data analysis and programming

Further information

Final application date: 10 December 2019.

Please send in individual applications with CV, motivational letter and grade transcripts. If you wish to partner with someone, simply note that in your application. 

Planned start: 1 February 2020, with some flexibility. 

Duration: 30 ECTS 

For questions regarding the project, welcome to contact

Majid K. Vakilzadeh, majid.vakilzadeh@zenuity.com

Ghazaleh Panahandeh, ghazaleh.panahandeh@zenuity.com

 

 

 

Or, know someone who would be a perfect fit? Let them know!

Gothenburg, Sweden

Lindholmspiren 2
417 56 Gothenburg, Sweden Directions recruitment@zenuity.com

Making safe and intelligent mobility real.

At Zenuity, we lead the global movement of crafting tomorrow's mobility with the software platform of choice. Our mission is to “Make safe and intelligent mobility real, for everyone, everywhere”. This statement marks our conviction and dedication to bring autonomous driving out on the streets for real and is at the center of everything we do.  

We could not dream of achieving this without our great teams of very talented people. We are on this journey together and our agile way of working is reflected throughout our entire organization; it is part of our culture and how we work, develop and grow together. 

Teamtailor

Career site by Teamtailor