direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Interactive Perception [1]


Action is a crucial part of the perceptual process. Humans interact with their environment constantly to reveal information and use the interaction to understand the consequences of their actions in the world. Interactive Perception exploits these ideas to build autonomous mobile manipulators that use interactions to perceive, understand and manipulate their environment. more to: Interactive Perception [2]

Representation Learning [3]


Truly versatile robots cannot rely on representations that are specifically hand-crafted for every task. Instead they must be able to learn these representations from experience. more to: Representation Learning [4]

Grasping [5]


Brushing teeth, eating, opening a door: humans solve the grasping problem countless times each day without thinking of it. However, even a 1-year-old child grasps more reliably than any existing grasping approach in robotics today. more to: Grasping [6]

Soft Robotics [7]


The inherent compliance of soft robots allows for safe and robust interaction. This, however, introduces new challenges for fabrication and control. Because of the flexibility and elasticity of the used materials, new solutions have to be found. And also topics like sensorization, where solutions exist for conventional, rigid-link robotics, have to be reconsidered for soft robotics. more to: Soft Robotics [8]

Soft Hands [9]


Using manufacturing techniques of Soft Robotics, we build rubber hands for grasping. Actuated pneumatically, they facilitate a predictable and robust grasping performance by complying to diverse object geometries and positions, thus easing the perception of grasp affordances. more to: Soft Hands [10]

Morphological Computation [11]

We research methods to quantify the contribution of a robot's morphology when executing a task, and how to use it to adapt robot morphology for better performance. more to: Morphological Computation [12]

Motion Generation [13]


How to find motion strategies that are robust in the real world? We combine control and planning under uncertainty to generate motion for mobile manipulators. more to: Motion Generation [14]

Protein Structure Prediction [15]


Proteins are hetropolymers consisting of 20 types of amino acids. The sequence of amino acids in a hetropolymer chain that constitute a particular protein is encoded in genes. more to: Protein Structure Prediction [16]

Protein Motion [17]


Understanding the function of a protein requires understanding the protein's motions behind that function. We work towards developing a "computational microscope" that simulates these motions computationally efficient and biologically accurate. more to: Protein Motion [18]

Heuristics for Ball Catching [19]


Is it better to use heuristics or optimization for control problems such as ball catching? more to: Heuristics for Ball Catching [20]

Check our Youtube Channel

------ Links: ------

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions

Copyright TU Berlin 2008