SwarmLab Projects

Lecturer:

Language:

The course will be held in English or German, depending on the participant's preferred language.

Participants:

All students of bachelor and master curriculums of the faculty are eligible to attend the course. The course can be taken as Digital Engineering Project, Inter-Disciplinary Project or Team-Project. The actual type of course depends on the needs of the students and the available Topics.

For each project, it is required that you attended the lecture "Introduction to Robotics" and completed with a "Schein" or passed the exam.

It is mandatory for a participant to have background knowledge in at least one of the following topics:

Robotics
Programming in C/C++ or Python (depending on project)
Theory and Algorithms of Swarm Intelligence
Communications and Networks
Development of Embedded Applications in C
Robot Operating System (ROS)
Linux Server Administration

How to Enter:

Please write an E-Mail to the responsible teacher and declare your interest in a topic. The teacher will organize individual meetings with the interested students.

Organization:

The course will be taken in groups of 3–5 Students per topic. The students and the groups will be chosen by us depending on your background. The individual topics are not fully fixed, extensions and modifications are possible depending on the skills and interest of participating students. This will be discussed in the first meeting. The result of each project is a working demonstration with commented source code and a written documentation indicating the general concept and a How-to to start the demo.

Available Topics:

DE-Project / Team project: Evaluation of multiple SLAM-Algorithms

in Cooperation with ifak e.V.

Participants may either select this topic as DE-Project, Interdisciplinary Team Project or Scientific Team Project in Bachelor or Master Studies at the FIN.

The aim of the project is to evaluate multiple Simultanious Localization and Mapping (SLAM) algorithms in the context of autonomous driving. The SLAM algorithms shall be tested on recorded datasets of the autonomous shuttle bus used in the AULA-KI project. The recorded datasets contain 3D-Lidar data, Inertial Measurement Unit (IMU) data and odometry data. The algorithms to be evaluated incorporate at least the following ones: Hector-Slam, GMapping, Cartographer, SIU-Slam.

Responsible Teacher: Christoph Steup

Project Requirements:

Experience in Robotics, e.g.,: the lecture "Introduction to Robotics" or other project incorporating robotics
Python- or C++-Programming

DE-Project / Team project: New Gazebo-based Simulation for the Robots of the robOTTO RoboCup @Work Team

in Cooperation with Team robOTTO

Participants may either select this topic as DE-Project, Interdisciplinary Team Project or Scientific Team Project in Bachelor or Master Studies at the FIN.

The participants will work on creating a fully integrated ROS-1-based simulation of the robots of the team. The goal is to model these robots regarding their components, kinematics, and dynamics. The simulation should be able to replace the physical robot to enable Hardware-In-The-Loop (HITL) and Software-In-The-Loop (SITL) tests. To this end, the current robot needs to be composed in Gazebo using existing 3D-Models and the sensors and actuators of the robot need to be replicated using existing plugins of Gazebo. Finally, the API of the robot has to be recreated through custom ROS-Nodes translating commands from the robOTTO Software Stack to the Gazebo Model. The main goal of this project is to model the base of the robot correctly regarding the 3D-shape as well as the dynamic parameters like torque/force of the motors, weights and weight distribution.

Responsible Teacher: Christoph Steup

Project Requirements:

Experience in Robotics, e.g.,: the lecture "Introduction to Robotics" or other project incorporating robotics
Python- or C++-Programming

Team project: Improving the Robustness of Multi-Robot Navigation with Driving Swarm

In this project, participants will perform experiments with the TurtleBot3 robots using the Driving Swarm framework. The goal of the project is to measure and improve the robustness of local planning within the Driving Swarm framework. Currently, the low-level planner used for Multi-Robot Navigation computes the control outputs of the robot to be optimal with respect to two constraints: Distance to obstacles and accuracy of trajectory following. This sometimes leads to deadlocks when both objectives are in equilibrium. The goal of the project is to increase the robustness of the local navigation to reduce deadlocks and the probability of collisions.

The improvement should be measured and quantified by experiments with up to 10 real and simulated robots.

Project requirements:

Only register for the project if you passed the course Introduction to Robotics
Knowledge in planning and control of mobile robots
Python Programming with ros2 and Jupyter

Responsible Teacher: Sebastian Mai

Additional Topics: on request