Staff

DLR German Aerospace Center
Institute of Robotics and Mechatronics
Cognitive Robotics
Oberpfaffenhofen
Muenchener Str. 20
82234 Wessling

telephone:	+49 8153 28-4794
email:	This email address is being protected from spambots. You need JavaScript enabled to view it.

--> Website: https://github.com/MarkusKnauer

DLR career

I started at the DLR in November 2019 as a working student at the department of Perception and Cognition (PEK) where I wrote my master thesis on "A persistent incremental learning approach for object classification of unseen categories using convolutional neural networks on mobile robots" (https://elib.dlr.de/135950/). Here I am also working on BlenderProc - A procedural Blender pipeline for photorealistic training image generation for Neural Networks (https://github.com/DLR-RM/BlenderProc). Since the end of 2020 I am a Research Scientist at the department of Cognitive Robotics where I am among other things working on the Factory of the Future (FOF/FOF-X) project.

 

Research Interests

• Learning from demonstration
• Probabilistic methods
• Machine learning
• Deep learning
• Continual learning
• Computer vision

Project Sites

• IROS 2022

Publications

 

• Maximilian Denninger, Dominik Winkelbauer, Martin Sundermeyer, Wout Boerdijk, Markus Wendelin Knauer et 3 al.:
  BlenderProc2: A Procedural Pipeline for Photorealistic Rendering
  Journal of Open Source Software, vol. 8 (82). Journal of Open Source Software, 2023. DOI 10.21105/joss.04901, ISSN 2475-9066. [elib]
• Markus Wendelin Knauer, Maximilian Denninger, Rudolph Triebel:
  HOWS-CL-25: Household Objects Within Simulation Dataset for Continual Learning
  Zenodo.org. 2022. DOI 10.5281/zenodo.7189434. [elib]
• Markus Wendelin Knauer, Maximilian Denninger, Rudolph Triebel:
  RECALL: Rehearsal-free Continual Learning for Object Classification
  In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), 2022-10-24 - 2022-10-26, Kyoto, Japan, 2022. DOI 10.1109/IROS47612.2022.9981968, ISBN 978-166547927-1, ISSN 2153-0858. [elib]
• Markus Knauer:
  A persistent incremental learning approach for object classification of unseen categories using convolutional neural networks on mobile robots
  Master's. Hochschule Kempten, 2020. [elib]
• Maximilian Denninger, Martin Sundermeyer, Dominik Winkelbauer, Dmitry Olefir, Tomas Hodan et 5 al.:
  BlenderProc: Reducing the Reality Gap with Photorealistic Rendering
  In: 16th Robotics: Science and Systems, RSS 2020, Workshops. 2nd Workshop on Closing the Reality Gap in Sim2Real Transfer for Robotics, Robotics: Science and Systems (RSS), 2020-07-12 - 2020-07-16, Virtuell, 2020. ISBN 978-0-9923747-6-1, ISSN 2330765X. [elib]