Header logo is
Independent Research Groups
Autonomous Vision

Max Planck Research Group for Autonomous Vision

We are interested in computer vision and machine learning with a focus on 3D scene understanding, parsing, reconstruction, material and motion estimation for autonomous intelligent systems such as self-driving cars or household robots. In particular, we investigate how complex prior knowledge can be incorporated into computer vision algorithms for making them robust to variations in our complex 3D world. You can follow us on GoogleScholar (paper email alert), on YouTube (video email alert) and on Read More

Autonomous Learning

Max Planck Research Group for Autonomous Learning

We are interested in autonomous learning, that is how an embodied agent can determine what to learn, how to learn, and how to judge the learning success. In particular, we focus on learning to control a robotic body in a developmental fashion. Artificial intrinsic motivations are a central component that we develop using information theory and dynamical systems theory. We work on reinforcement learning, representation learning, and internal model learning.

Dynamic Locomotion

We investigate principles of biomechanics and control of dynamic locomotion, in legged animals and robots.

We are extending research in biomechanics and neurocontrol by implementing and controlling custom designed, legged robots, and their simulated models. We see dynamic legged locomotion as the product of a tightly interconnected and adapted motor control, sensing, and mechanical system. Understanding the underlying principles that enable animals with limited control bandwidth to achieve both agile and robust locomotion is an exemplary key question in legged locomotion. Research at the Dynamic Locomotion Group focuses on applying legged robots and their models to provide biomechanically relevant locomotion data. This allows us to qualitatively and quantitatively analyze and compare legged locomotion, in robots and animals. We are interested in testing and applying both existing locomotion control concepts, and learning new concepts of locomotion control. We are especially interested in bip... Read More

Probabilistic Numerics

The Independent Max Planck Research Group on Probabilistic Numerics

Numerical Problems --- linear algebra and optimization, integration and the solution of differential equations --- are the computational bottleneck of artificial intelligent systems. Intriguingly, the numerical algorithms used for these tasks are also compact little intelligent agents themselves. They estimate unknown / uncomputable quantities by observing the result of feasible computations. They also actively decide which computations to perform.  The Research Group on Probabilistic Numerics studies this philosophical and mathematical connection between computation and inference. We aim to build a theoretical understanding of numerical computer algorithms as agents acting rationally under uncertainty. We analyse existing algorithms from this viewpoint, and propose novel algorithms that provide functionality for key computational ch... Read More

Statistical Learning Theory

Max Planck Fellow Group

We work on the theoretical analysis of machine learning algorithms. Our current focus is on comparison-based learning algorithms and on algorithms on random graphs and networks. The group is lead by Ulrike von Luxburg, the funding comes from a Max Planck Fellowship. The groups by Ulrike von Luxburg are distributed between the Max Planck Institue and the University of Tübingen, our main webpage is the one at the university . The Max Planck branch of our group consists of the following people: Ulrike von Luxburg (Research Group Leader) Michael Perrot (Postdoc) Damien Garreau (Postdoc)

Micro, Nano, and Molecular Systems

Our group has broad interests in the interaction of optical, electric, and magnetic fields with matter at small length scales. We work on new 3-D fabrication methods, self-assembly, actuation, and propulsion. We have observed a number of fundamental effects and are developing new experimental techniques and instruments.

Smart Nanoplasmonics

The nanometer scale is where the chemistry, biology, and materials sciences converge. The optical properties of metal nanoparticles have been an object of fascination since ancient times. When light interacts with a metal nanoparticle (for example a gold colloid in a stained church window), collective oscillations of conduction electrons known as particle plasmons are excited.