Rheinische Friedrichs-Wilhelms-Universität Bonn, Germany (Coordinator)

Autonomous Intelligent Systems Group (AIS)
The University of Bonn (UBO) is one of the leading public research universities of Germany. Founded in 1818, the University of Bonn offers a large number of undergraduate and graduate programs in a range of subjects. The University of Bonn has 520 professors and about 31,000 students. The Computer Science Institute has 20 professors, about 130 researchers, and about 25 non-scientific staff members. The institute has a long tradition in robotics research, especially in the areas of probabilistic robotics and service robots. The proposed research will be carried out in the Autonomous Intelligent Systems Group headed by Prof. Sven Behnke. The group conducts research in the areas of cognitive robotics and computational intelligence.



Our team NimbRo Rescue was the best ranked European team at the DARPA Robotics Challenge (DRC) Finals in Pomona, USA, comming in 4th overall.

Our teams NimbRo Manufacturing, NimbRo Logistics, and NimbRo Copter have been admitted to Stage II of the European Robotics Challenges (EuRoC). Together with industrial end-users, they will address use cases in the domain "Factories of the Future"


The Autonomous Intelligent Systems group conducts research in the areas of cognitive robotics and computer vision.

Cognitive Robotics

Cognitive robots represent the next step in the fusion of machines, computing, sensing, and software to create intelligent systems capable of interacting with the complexities of the real world. They are the physical embodiment of machine intelligence. Key challenges in constructing these robots include the systematic treatment of uncertainties, the modeling of the environmental state, the coordination of teams of cooperating robots in dynamic environments, the interaction with humans, development, and learning.

Examples for cognitive robot systems are humanoid robots, which resemble the human body plan and rely on human-like senses. Our robots are playing soccer in the RoboCup Humanoid League and perform domestic service tasks in the RoboCup@Home League. They are also used for intuitive multimodal communication with humans in a museum tour-guide scenario.
Other cognitive robots we investigate include autonomous micro aerial vehicles (MAVs), bin picking robot manipulators, and exploration robots.

Computer Vision

In the area of computer vision we investigate object categorization, object-class segmentation, semantic mapping, and action recognition. In particular, we focus on deep learning methods using hierarchical representations in neural networks or graphical models. 

One example for such a deep learning architecture is the neural abstraction pyramid, which resembles some aspects of the human visual system. This hierarchical recurrent artificial neural network can be trained to learn e.g. face detection and image reconstruction tasks.