Self-driving Tractors – Increasing Safety with Obstacle Detection in 3D

PhD defence, Friday 20 April 2018, Mikkel Fly Kragh.

2018.04.20 | Trine Berndt Turtiainen Scheelke

Mikkel Fly Kragh

During his studies, Mikkel Fly Kragh has investigated modern lidar-sensing technology for 3D obstacle detection and recognition in agricultural environments. The applied lidar consists of multiple lasers that measure distances to the environment by scanning 360° horizontally 10 times a second. Each scan generates a 3D point cloud with 70,000 range measurements. Mikkel Fly Kragh has studied and proposed a number of methods for analyzing these point clouds to detect obstacles such as humans, animals and vehicles. These must all be avoided by an agricultural robot when operating autonomously in a field. The research findings have shown that recent advancements in urban autonomous driving can be transferred to agriculture. Lidar-sensing combined with color and thermal cameras can increase detection accuracy and safety, and deep learning algorithms can automatically learn obstacle appearances and shapes when trained on large-scale recorded datasets.

The PhD degree was completed at the Department of Engineering, Science and Technology, Aarhus University.

This résumé was prepared by the PhD student.

Time: Friday 20 April 2018 at 13.00
Place: Building 5125, room 114E, Finlandsgade 22, 8200 Aarhus N.
Title of PhD thesis: Lidar-Based Obstacle Detection and Recognition for Autonomous Agricultural Vehicles
Contact information: Mikkel Fly Kragh, e-mail: mikkelkragh@gmail.com, tel.: +45 51761455


Members of the assessment committee:

Deputy Director Dr. Juan Nieto, Institute of Robotics and Intelligent Systems, Autonomous Systems Lab, ETH Zurich, Switzerland
Associate Professor Kim Steenstrup Pedersen, Department of computer science, University of Copenhagen, Denmark
Associate Professor Stefan Hallerstede (chair), Department of Engineering, Aarhus University
Main supervisor:
Senior Researcher Rasmus Nyholm Jørgensen, Department of Engineering, Aarhus University
Co-supervisor:
Professor (Docent) Henrik Karstoft, Department of Engineering, Aarhus University
Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Science and Technology/GSST,
Ny Munkegade 120, building 1520, rooms 128-134, 8000 Aarhus C.

PhD defence
Comments on content: 
Revised 16.04.2018