Institute for Artificial Intelligence

Research in Artificial Intelligence for Autonomous Mobile Robots

Technologies
python, ros, c++, lisp, unreal engine
Topics
artificial intelligence, robotics, simulation, perception, unreal engine
Research in Artificial Intelligence for Autonomous Mobile Robots

The Institute for Artificial Intelligence (IAI) at the University of Bremen, Germany, headed by Prof. Michael Beetz, investigates methods for cognition-enabled robot control. The research is at the intersection of robotics and Artificial Intelligence (AI) and includes methods for intelligent perception, dexterous object manipulation, plan-based robot control and knowledge representation for robots. Robots performing complex tasks in open domains, such as assisting humans in a household or collaboratively assembling products in a factory, need to have cognitive capabilities for interpreting their sensor data, understanding scenes, selecting and parameterizing their actions, recognizing and handling failures and interacting with humans. IAI develops solutions for these kinds of issues, implements and test them on the robots in our laboratory. A particular focus of the group is on the integration of individual methods into complete cognition-enabled robot control systems and the release of the developed software as open-source libraries.

2018 Program

Successful Projects

Contributor
Shixin Li
Mentor
jawo, Ferenc Balint-Benczedi
Organization
Institute for Artificial Intelligence
Proposal for RoboSherlock GSOC 18
This project targets at enabling the current RoboSherlock to work in form of parallel pipeline, which also includes merging results of different...
Contributor
Kaivalya Rawal
Mentor
Daniel Nyga
Organization
Institute for Artificial Intelligence
Markov Logic Networks in Python: PracMLN
Markov Logic Networks (MLNs) are a generalisation of first-order logic and probabilistic graphical models, thus forming a powerful mechanism of...
Contributor
Shingo Kitagawa
Mentor
Alexis Maldonado, Ferenc Balint-Benczedi
Organization
Institute for Artificial Intelligence
Implementation of Deep Learning Annotators written in Python into RoboSherlock
In GSoC, I propose to introduce deep learning annotators in RoboSherlock for more various task. Because many deep learning frameworks and...
Contributor
Mircea-Tudor Chifor
Mentor
Asil Kaan Bozcuoğlu, Andrei Haidu
Organization
Institute for Artificial Intelligence
Eye Tracking GUI Integration
My proposed Project consists of developing a GUI with Unreal Engine for Eye Tracking and any adjacent work involving the aforementioned tehnology.
Contributor
An T. Le
Mentor
Ferenc Balint-Benczedi
Organization
Institute for Artificial Intelligence
Flexible perception pipeline manipulation for RoboSherlock
The project proposes flexible pipeline handling mechanism for RoboSherlock framework. The current state of RoboSherlock implementation does not allow...
Contributor
Björn Veit
Mentor
Andrei Haidu
Organization
Institute for Artificial Intelligence
KnowRob visualization in RobCoG
The RobCoG project is presenting a new perspective on how robots are supposed to learn everyday tasks. Learning from humans essentially playing a...