Deep Learning 

Our work in Deep Learning is focused on Computer Vision with emphasis on object categorization, object-class segmentation, and action recognition tasks. Deep Learning methods produce a hierarchy of representations using multi-layered models, such as deep neural networks or deep graphical models. To accelerate calculations with GPUs, we make use of the Nvidia CUDA framework.

        

Projects: 

• BMBF project "WestAI – Service Center for Artificial Intelligence"
  
  
• The Lamarr Institute for Machine Learning and Artificial Intelligence, principal investigator
  
  
• BMBF project "BNTrAinee: Bonn Transdisciplinary Education in Artificial Intelligence"
   
  
• 2021-2025: BMBF/ANR project "Learn2Grasp: Learning Human-like Interactive Grasping based on Visual and Haptic Feedback"
   
  
• DFG Cluster of Excellence “PhenoRob–Robotics and Phenotyping for Sustainable Crop Production”, principal investigator, co-lead of Core Project 1: “In-field 4D Crop Reconstruction”
  
  
• BMBF Competence Center “Machine Learning Rhine-Ruhr (ML2R)”, project "Self-Supervised Learning of Structured Visual Representations"
  
  
• Fraunhofer project "Collaborative Perception and Prediction with Smart Edge Sensors"
  
  
• DFG Research Unit FOR 2535 "Anticipating Human Behavior": Learning Hierarchical Representations for Anticipative Human-Robot Collaboration
   
• DFG: Automatic Reconstruction of Root Systems from MRI
   
• DFG Research Training Group 1572 Bionics: Learning Hierarchial Invariant Features for Action Recognition 
  

     

                 




     University of Bonn, Institute for Computer Science, Computer Science VI - Intelligent Systems and Robotics    Impress    Data Privacy Statement ; NimbRo; Robotics