TU Berlin

Robotics and Biology LaboratoryProjects

Fachgebietslogo RBO

Page Content

to Navigation

Amazon Picking Challenge 2015


In May 2015, our Team RBO won a prestigious international robotics challenge, the Amazon Picking Challenge. This challenge aims to solve one of the last problems in warehouse automation: identifying and grasping objects from a warehouse shelf. Our robot was able to secure the lead by picking 10 out of 12 objects, outperforming 25 teams from Europe, USA and Asia, amongst them teams from the Massachusetts Institute of Technology (MIT), UC Berkeley as well as many robotics companies. more to: Amazon Picking Challenge 2015

Physical Exploration Challenge


This project addresses a fundamental challenge in the intersection of machine learning and robotics. The machine learning community has developed formal methods to generate behaviour for agents that learn from their own actions. However, several fundamental questions are raised when trying to realize such behaviour on real-world robotics systems that shall learn to perceive, actuate and explore degrees of freedom (DoF) in the world. These questions pertain to basic theoretical aspects as well as the tight dependencies between exploration strategies and the perception and motor skills used to realize them. more to: Physical Exploration Challenge

Soft Manipulation (SOMA)


The main obstacle to a wide-spread adoption of advanced manipulation systems in industry is their complexity, fragility, lack of strength, and difficulty of use. This project describes a path of disruptive innovation for the development of simple, compliant, yet strong, robust, and easy-to-program manipulation systems. The idea is: Soft Manipulation (SoMa). The project is funded by European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement 645599. more to: Soft Manipulation (SOMA)

Robotics-Specific Machine Learning (R-ML)

This project will develop robotics-specific machine learning methods. The requirement for such methods follows directly from the no-free-lunch theorems (Wolpert, 1996) which prove that no machine learning method works better than random guessing when averaged over all possible problems. The only way to improve over random guessing is to restrict the problem space and incorporate prior knowledge about this problem space into the learning method. more to: Robotics-Specific Machine Learning (R-ML)

Photo Cross-linking/mass spectrometry (CLMS)

This project develops a structure determination method targeting proteins inaccessible by established techniques. This will be enabled by novel experimental protocols yielding high-density cross-linking and custom tailored computational methods to model protein structures from this data. more to: Photo Cross-linking/mass spectrometry (CLMS)

Capabilities and consequences of recursive, hierarchical information processing in visual systems


We investigate human and robot perception. The goal is to develop a constructive understanding of perceptual information processing, capitalizing on the analytic-synthetic loop. Our implementation of this concept is based on the concept of "optical cortex and robotic interactive perception algorithms". This resemblance is so striking because it spans various levels of abstraction and matches. Indeed, this computational architecture enables predictions that match observations in humans. more to: Capabilities and consequences of recursive, hierarchical information processing in visual systems


Quick Access

Schnellnavigation zur Seite über Nummerneingabe