lunduniversity.lu.se

Automatic Control

Faculty of Engineering, LTH

Automatic Control  

Test and trace

Test and trace offers a promising path to halt the spread of an infectious disease in its tracks. But how accurate does the testing need to be? And how fast must cases be traced?

Nature paper

Model used to evaluate lockdowns was flawed

LTH best Master's thesis

Johanna Wilroth has been awarded the prize "LTHs Jubileumsstipendium 2020" for the best master thesis at LTH. In her thesis "Domain Adaptation for Attention Steering," Wilroth studied novel algorithms for improving the performance of hearing aids using EEG signals in combination with auditory input. The master thesis was done at the Department of Automatic Control, with Carolina Bergeling as main supervisor, in collaboration with the research center Eriksholm/Oticon in Denmark. The collaboration also involved the departments of Psychology and Mathematical Statistics at Lund University.

Charlotta Johnsson new rector for LTH Campus Helsingborg

Master Thesis dispels a common argument against wind power

A common notion is that only nuclear power and hydro power can keep the Swedish power grid stable at 50 Hz. Something that is necessary for the system to function normally, and prevent blackouts. A new Master Thesis by Johan Lindberg, at the Department of Automatic Control, shows that also wind power can manage this task.

Paper Award

We congratulate Marcus Greiff (to the right in the photo) and co-authors Anders Robertsson (left) and Karl Berntorp (middle) who was awarded the 2020 IEEE CCTA Best Student Paper Award for the paper "MSE-Optimal Measurement Dimension Reduction in Gaussian Filtering”.

Researchers: ”Beware of complex corona models – they can surpass reality”

Outstanding master's thesis

Frida Heskebeck is a recently employed PhD student at the Department of Automatic Control. She has been awarded a scholarship from the Karl-Erik Sahlberg Foundation for an outstanding master's thesis project in chemistry. The motivation: "Antibodies are target-searching drugs used for the treatment of severe diseases. The use of antibody-based drugs is, among other things, limited by expensive production methods. In her master's thesis, Frida gives an excellent description of how advanced process methods can contribute to improved antibody production. The presentation of results and suggestions of 'Future Work' is done excellently in the thesis."

Lund Formula Student

The department has a collaboration with the Lund Formula Student team, who are developing a fully autonomous race car to compete in Formula Student events all across Europe.

Artificial intelligence

Within the field of adaptive control, Automatic Control were doing AI research already in the 70s

The future of drones

Automatic Control is part of a university-wide collaboration project on unmanned aerial vehicles
•••
 

M.Sc by Sond & Johnsson: Controlling a sliding contact on an electric vehicle with computer vision and AI

Seminarium

From: 2021-01-28 13:15 to 13:45
Place: https://lu-se.zoom.us/j/65008592425
Contact: johan [dot] gronqvist [at] control [dot] lth [dot] se
Save event to your calendar

Controlling a sliding contact on an electric vehicle with computer vision and AI

Abstract:

Emission from vehicles is a massive problem and contributes to the climate change on our planet. One solution that people are turning to is electrical propulsion instead of fossil fuel. There are however problems with putting big batteries on vehicles. They are expensive to build, require rare minerals and the process of creating batteries emits plenty of greenhouse gas. To reduce the need of big batteries Elonroad is creating a way of charging ground vehicles while driving. This works by putting rails in roads and sliding contacts underneath vehicles. For this to work the sliding contacts and the rail needs to stay aligned while driving. In this thesis the problem is solved by controlling the sliding contacts position with use of cameras and machine learning. The proposed structure is to use a pre-trained neural network called \textit{MobileNet} together with a custom neural network to estimate the position of the sliding contact. The estimated position is then used as input to a PID controller that controls the position of the sliding contact with a motor.

Students: 

Axel Sondh

Björn Johnsson

Supervisors:

Johan Grönqvist*, Dept. of Automatic Control, LTH

Dan Zethraeus, Elonroad AB

Examiner:

Kristian Soltesz

 

* Contact person

The presentation will be held using Zoom: https://lu-se.zoom.us/j/65008592425



More events

Recent Publications

Open PhD student position

in automatic control with focus on cloud. Apply before 2021-02-19

Open Postdoc position

in Automatic Control. Apply before Jan. 31 2021.

Covid-19 teaching policy, spring 2021

Welcome to KC4!

In May, we moved to temporary offices at KC4 in Kemicentrum. Here we will stay for two years while the M-building is being renovated. See "contact" (in About) for the new visiting adress.

Follow us on Linked In

MSc programme in Machine Learning, Systems and Control

Formula Student

The department has a collaboration with the Lund Formula Student team, who are developing a fully autonomous race car to compete in Formula Student events all across Europe. They are always looking for interested and talented team members. If you are interested in a wide variety of technologies such as neural networks, control theory, ROS, etc, please visit their website or contact them at: technical.driverless@lundformulastudent.se.