MSc. Thesis: Model validation for autonomous trucks

One of the most challenging issues for automated vehicles is: how can it be ensured that the decisions taken by the automated vehicle are safe? Safe decisions require accurate predictions of the future behavior of the automated vehicle. To this end, mathematical models are typically employed, and the quality of those models are thereby what enables an assessment of whether or not a decision is safe. This necessitates a validation of the models used, and a quantification of the confidence one can have in them.
While parts of the modelling of the dynamics of road vehicles follows from first principles, a major part (e.g. the behavior of the tires) are often based on empirical evidence. On top of this, there are a number of physical phenomena that are not captured by the standard models, many model parameters are uncertain, measurements are inexact and non-modeled disturbances are often present. For this reason, the models are always associated with some degree of uncertainty. The process of quantifying such uncertainty is often referred to as model validation.
Data-driven model validation is an important topic in the field of system identification. Most methods form some kind of statistics around the model residuals (i.e. the part of the data that could not be explained by the model) in order to infer the quality of the model. The aim of this thesis is to perform an extreme value analysis on the model residuals to predict the likelihood of seeing extreme model errors.
Tasks
  • Familiarizing with dynamic models of articulated vehicles
  • Familiarizing with existing software for model validation
  • Implement necessary methods to perform an extreme value analysis
  • Perform an extreme value analysis on the model residuals
  • Documentation of results
Suitable background
Master student in engineering mathematics, engineering physics, automation and mechatronics, automotive engineering, control theory or similar.
Required skills
Good programming skills (MATLAB and/or Python).
Nice to have skills
Knowledge of Extreme value theory, System identification, Vehicle dynamics modelling, Control & systems theory, Numerical methods for optimization, Numerical methods for ODEs.
Language: English
Starting date: January 2020
Number of students: 1-2
Academic supervisor
Prof. Holger Rootzén, Mathematical Sciences, Chalmers University of Technology
Industrial supervisors
Emil Klintberg, Vehicle Automation, Volvo Group
Robert Hult, Vehicle Automation, Volvo Group, +46 313229292

会社概要

The Volvo Group is one of the world’s leading manufacturers of trucks, buses, construction equipment and marine and industrial engines under the leading brands Volvo, Renault Trucks, Mack, UD Trucks, Eicher, SDLG, Terex Trucks, Prevost, Nova Bus, UD Bus and Volvo Penta.

Volvo Group Trucks Technology provides Volvo Group Trucks and Business Area's with state-of-the-art research, cutting-edge engineering, product planning and purchasing services, as well as aftermarket product support. With Volvo Group Trucks Technology you will be part of a global and diverse team of highly skilled professionals who work with passion, trust each other and embrace change to stay ahead. We make our customers win.

あなたについて知らせてください

選考プロセス

応募

応募頂いた後に、応募確認のeメールが送信されます。この後も、あなたの個人プロフィールを更新することができます。

面接

面接に進んで頂く場合は、その旨を連絡致します。その後のステップについてもお知らせいたします。

選考

採用者が決定したことは全ての候補者に通知されます。 あなたは私たちのデータベースにあなたの履歴書を保存して、あなたのプロフィールにマッチする他の仕事を探すことが出来ます。

イントロダクション

勤務を開始する際は、あなたがすぐにチームの一員となり、最高の形で仕事ができるようにイントロダクションを受けます。

お客様の声

同様の職種