Open Source Software and Hardware

Software framework

The software framework is a software written in Java that runs on any PC. It contains the central AI and is responsible for receiving camera data, filtering the data and communicating with the robots by calculating decision in the AI.


The electronics package includes schemas and layout of all electronics.
They are designed with Autodesk EAGLE.


CAD files and PDF drawings of all parts.
2011 files use CATIA.
2013 and 2014 files use Autodesk Inventor 2013.
2016, 2017, and 2018 files use Autodesk Inventor 2016.
2019 and 2020 files use Autodesk Inventor 2019.


The code running on the microcontrollers of our robot. Projects are using Eclipse as IDE and the GNU GCC compiler.
Each archive contains a PDF file with setup instructions.

TIGERs grSim Simulator

Adapted version of the grSim simulator to work with our software. It includes automated install scripts for Linux, Visual Studio support for Windows and better ball simulation.

Autonomous Referee

Autonomous referee software for detecting rule violations (2014) and managing a full game (2016)

SSL Augmented Reality App

An Augmented Reality App that visualizes AI decisions in a live video or video file send through network in a protobuf packet.

Documentation and other files

All release files can be browsed through the buttons below.

(Seminar) Papers

This section lists papers written by Tigers team members during their studies or with a strong relation to the RoboCup domain.

Published Title Author
Dec 04, 2020 Robust On-Board Image Recognition for Autonomous Robot-Ball Interaction Litzelmann, R. & Ratzel, M. Abstract Paper

In the Small Size League (SSL) soccer competition of the Robot World Cup (RoboCup), the TIGERs Mannheim team uses an image recognition system that recognises the ball directly with cameras on the robots. This reduces the reliance on the league-internal vision system. Based on a previous work, this study report aims at centralising the configuration system and enhancing the detected ball position using undistortion and backprojection. The centralisation avoids deviating configuration states in the multi-robot environment. The former configuration system is modifiedand extended to the robots’ Firmware by introducing a new concept. An undistortion model with few parameters is successfully generated and trained. It combines high performance and accuracy. Additionally, the detected ball position is projected back into the three-dimensional space, which contributes to a more effective control of the robot.The results of this study report reflect an improvement in the overall robustness of the image recognition, although the new system has yet to prove itself in a competitive tournament environment like RoboCup

Dec 04, 2020 Ball State Estimation Based on a Near-Field Low-Resolution Infrared Sensor Array Messerschmidt, Marius Abstract Paper

For a team in the RoboCup’s Small Size League (SSL) it is crucial to accuratelyknow the ball position at any point in time. The regular method of obtaining this information is to receive the location from the leagues vision system. However, besides the limited accuracy of the system, there are situations where it can not detect the ball fully. Therefore, a system to detect the ball is added to the robot in this report. I uses a combination of infrared emitters and receivers to detect the signal that is reflected by the ball. Different strategies for the ball position estimation are shown in this report and a combination of a polynomial fit and a tiny neural network is used to predict the position of the ball up to a few millimeters of accuracy. If however, there are other obstacles in front of the robot, such as an opponent robot,the system looses a lot of its accuracy but is still able to detect the presence of the ball and to estimate its position with an error of about 2 centimeters in each direction.

Jun 21, 2019 On-Board Computer Vision for Autonomous Ball Interception Seel, F. & Jut, S. Abstract Paper

Implementing the Vision-Blackout Technical Challenge in the Robocup Small Size League.

Jun 29, 2018 Rework of the Coordination of Offensive Actions in the RoboCup Small Size League Leipscher, U. Abstract Paper

In the Small Size League (SSL) soccer competition of the Robot World Cup (RoboCup), fast passes between robots are the main tool to overcome the defence of the opponent team and allow for successful goal kicks. Most teams have developed tactics to intercept passes and gain ball control. Therefore, reliable analysis of the current situation and the decision if a pass is feasible are necessary. In this work, different pass rating functions are introduced and tested. Focusing on simplicity and reliability, the pass rater use distances of the opponent robots to the pass line as basis for their ratings. An analysis of simulated soccer games using the new pass raters shows similarly high success rates for passes. Finally, the implemented software allows simple exchange and configuration to adjust to different opponents.

Aug 09, 2017 Real-Time Online Adaptive Feedforward Velocity Control for Unmanned Ground Vehicles Ommer, Nicolai Abstract Paper

Online adaptation of motion models enables autonomous robots to move more accurate in case of unknown disturbances. This paper pro-
poses a new adaptive compensation feedforward controller capable of online learning a compensation motion model without any prior nowledge to counteract non-modeled disturbance such as slippage or hardware mal-functions. The controller is able to prevent motion errors a priori and is well suited for real hardware due to high adaptation rate. It can be used in conjunction with any motion model as only motion errors are compensated. A simple interface enables quick deployment of other robot systems as demonstrated in Small Size and rescue Robot RoboCup leagues.

Jul 16, 2016 Development of an Autonomous Referee Software for the Small Size League Magel, Lukas Abstract Paper


Jun 03, 2015 Design and Implementation of Dynamic Offensive Strategies in RoboCup Small Size League Geiger, Mark Abstract Paper

The work described in this report includes the implementation of several new
modules and analysis methods within Sumatra that form a nearly completely
redesigned o offensivestrategy. One key task described in this report is the handling
of multiple robots in the offensive strategy to support and improve passing and
redirecting to build a dynamic and intelligent offensiveplaying behavior.
The newly created offensive design enables more exible and more scoring dangerous
o ensive plays. Furthermore the newly created code is more reliable and easier to

Mar 19, 2015 Position Control of an Omnidirectional Mobile Robot Ommer, Nicolai Abstract Paper

Moving robots in the RoboCup Small Size League with fast reaction and low latency is crucial for the overall performance of a team. A good movement control is important to overcome the frictions of the wheels of the omnidirectional robots. Because modeling the friction is quite complex, we applied a learning algorithm based on Relative Entropy Policy Search for learning an optimal movement policy. Experiments in the simulation and with a real robot show that we are able to learn a policy that leads us to a desired target state.

Jun 21, 2013 Verbesserung der Taktischen Spielfeldanalyse - Analyse / Auslagerung von Berechnungen auf die GPU Posovszky, Philipp Abstract Paper

Diese Studienarbeit befasst sich mit dem Thema der Analyse eines Spielfeldes des Robocup in der Small Size League. Dabei war das Ziel, die aktuelle Methoden zur Spielfeldanalyse in der Software „Sumatra“ aus Performancetechnischer und Analytischer Sicht zu verbessern. Dazu wurde die aktuelle Analyse auf die Grafikkarte ausgelagert um eine besser Performance zu erzielen. Desweitern wurde die Distanzfunktion, welche nach der Euklidischen Distanz berechnet wird, im alten Analyse-Verfahren durch die Mahlanobis-Distanz ersetzt. Dies ermöglicht es einen Miteinbezug der Geschwindigkeit eines einzelnen Roboters in das Analyseverfahren. Zusätzlich wurde noch für den Play-Entwickler einer Klasse implementiert, welche es ermöglicht Informationen aus dem Analyse-Feld abzuleiten.

Jun 03, 2013 AI Architecture and Standard Game Strategies in RoboCup SSL Ommer, Nicolai Abstract Paper

In the RoboCup SSL one of the key challenges are good strategies for coordinating all robots with the aim of scoring goals. The team TIGERS Mannheim uses a central software called Sumatra which has a good base for creating and choosing good strategies. There are, however, some drawbacks in the architecture and Sumatra is still missing some good strategy implementations. Many developers worked on the strategies and many left the team afterwards. Nobody had an overview of currently active plays and their status. With this report, the whole AI architecture and all implemented strategies, called plays and roles, were analysed and optimized. The aim was to get a complete overview of all strategies and make it easier to hold the overview within the code. Another aim was to make the development of plays better understandable by creating a documentation and clean up and document the code of existing plays. The new architecture enables more flexibility, less redundant code and better under- standability. Deprecated plays and roles were removed and all existing plays tested and documented. Several features were added to the GUI of Sumatra to help developers with testing their work.