Bachelor Project: Vision-based Robot Control

Tutor: Alexander Golkowski, Peter Roch, Bijan Shahbaz Nejad

The goal of this bachelor project is to familiarize students with basic problems related to the control of autonomous mobile robots. Within the project, participants will be implementing the control logic of a mobile robot that can perceive its environment through different optical sensors, whereby webcams will be the main optical sensor for fast image processing.

Thereby, students will get in touch with the OpenCV library that implements a broad range of computer vision algorithms as well as the ROS framework which simplifies the development of robotic applications by faciliating the implementation of loosely coupled software components.

As hardware platform, the participants will be using webcams and the TurtleBot 2 or Turtlebot 3. TurtleBots are low-cost, open source robot kits that can be used to realize a broad spectrum of different robotic applications. A TurtleBot typically integrates different actuators, e.g. motors that drive the robot’s wheels, sensors, e.g. a LIDAR or an IMU, a base controller and a battery. Depending on the situation, a simulation of controlling the Turtlebots in Gazebo may take place instead.

Participants in this course are expected to be highly motivated and must have a solid understanding of one programming language, knowledge of programming in C++ are of advantage. In addition, students should be familiar with Linux-based command line tools (e.g. Bash, SSH, etc.) Note that due to the limited availability of TurtleBot hardware, the number of participants in this project is strictly limited. If you want to participate in this course, please send an email to alexander.golkowski@uni-due.de to indicate your interest.

This course may be held in German and English depending on the participants. The project is suitable for students at the bachelor level. If you are not sure whether you fulfill the requirements or if you have any questions, please send an email to alexander.golkowski@uni-due.de.

Due to the ongoing situation regarding COVID-19, it is necessary for the participants to send an email to alexander.golkowski@uni-due.de for the initial registration. You will then be added to the Moodle course, where the procedures and the project material will be made available.