Markus Knauer (@KnauerMarkus) header
Markus Knauer (@KnauerMarkus) profile picture

Markus Knauer

@KnauerMarkus

Research Scientist @ German Aerospace Center (DLR) & PhD + TA @ TUM, interested in making robots smarter. Machine Learning, Deep Learning, Active Learning, AI.

 Munich, Bavaria
markusknauer.github.io
Joined January 2018
  • Tweets44
  • Following96
  • Followers30
🚀 New paper in IEEE RA-L! IROSA: Interactive Robot Skill Adaptation using Natural Language Tell a robot "go faster" or "there's an obstacle" - it adapts. The LLM selects validated tool functions, no direct robot control: a zero-shot, local LLM. #robotics #LLM #IROS2026 #HRI 👇
1
1
3
466
Heading to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) #IROS2026 in Pittsburgh — I'll be there for the full week, 27 Sep – 1 Oct, workshops included, and would love to connect. Here's where you'll definitely find me. #Robotics #RobotLearning #HRI
Image from Markus Knauer (@KnauerMarkus)
1
1
44
markusknauer.github.io/proje…
IROSA: Interactive Robot Skill Adaptation with Natural Language

IROSA: Interactive Robot Skill Adaptation with Natural Language

IROSA adapts robot skills through natural language with a tool-based LLM architecture over Kernelized Movement Primitives. Published in IEEE RA-L 2026.

markusknauer.github.io
7
Teaching a robot a new skill from a handful of demonstrations, then correcting it in seconds: by pushing it, saying what to change, or clicking in a GUI. That's MOMO, now accepted at #IEEE RA-P. I led this one: 13 authors, 4 PhD projects, one system working on real hardware. – at Munich, Germany
1
2
79
More infos: markusknauer.github.io/proje…
MOMO: Physical, Verbal & Graphical Robot Skill Adaptation

MOMO: Physical, Verbal & Graphical Robot Skill Adaptation

MOMO unifies physical, verbal and graphical robot skill adaptation on a 7-DoF torque-controlled robot. Published in IEEE RA-P 2026.

markusknauer.github.io
1
12
Today I submitted my PhD dissertation. 🎓🎉 After years of research at the German Aerospace Center (DLR) and TU Munich, my work on data-efficient robot skill learning through interactive imitation learning is finally between two covers. #PhD #Robotics #MachineLearning #DLR #TUM – at Munich, Germany
Image from Markus Knauer (@KnauerMarkus)
2
56
Heading to #ICRA2026 in Vienna (1–5 June) — would love to connect. I’ll give two talks from my PhD at #DLR & #TUM. Both tackle the same goal: letting people teach and adapt robot skills through language, no code required. Links in the comments 👇 #Robotics #RobotLearning #HRI
Image from Markus Knauer (@KnauerMarkus)
1
2
27
markusknauer.github.io
Markus Knauer — Robotics & AI Researcher

Markus Knauer — Robotics & AI Researcher

Research Scientist at DLR and PhD candidate at TUM. I develop methods for interactive robot learning and language-guided motion adaptation.

markusknauer.github.io
10
Markus Knauer retweeted
Sebastian Jung (@sjung0) profile picture
Sebastian Jung@sjung0Feb 10
Curious? Try it out yourself! The code and checkpoints are publicly available: 🌐 Website: sebastian-jung.github.io/nem… 💻 GitHub: github.com/DLR-RM/nemo 📄 ArXiv: arxiv.org/abs/2602.04343 #ComputerVision #Robotics #AI #3DVision #PoseEstimation #MachineLearning #NeMO
Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception

Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception

NeMO encodes few RGB template views into a geometry-aware sparse 3D point cloud for 6DoF pose estimation, object detection, and segmentation — no retraining required. 3DV 2026 Oral.

sebastian-jung.github.io
1
1
1
56
Markus Knauer retweeted
Sebastian Jung (@sjung0) profile picture
Sebastian Jung@sjung0Feb 10
Excited to share that our NeMO🐠 paper got accepted as an Oral at #3DV2026! 🗣️🎉 Tired of needing 3D CAD models for 6DoF Pose Estimation? 🛑 No time to train a new model for every object? 🛑 Don't look further!
1
1
4
78
Markus Knauer retweeted
Sebastian Jung (@sjung0) profile picture
Sebastian Jung@sjung0Apr 21
🚀 Exciting News: TAPNext++ will be presented at CVPR 2026! I’m thrilled to share our latest work, "TAPNext++: What's Next for Tracking Any Point (TAP)?", completed during my time as a Student Researcher at Google. 🧵👇
2
16
3
109
10,175
IEEE Explore Paper link: doi.org/10.1109/LRA.2026.367… ArXiv paper link: arxiv.org/abs/2603.03897
IROSA: Interactive Robot Skill Adaptation Using Natural Language

IROSA: Interactive Robot Skill Adaptation Using Natural Language

Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these...

ieeexplore.ieee.org
1
21
Arrived at IROS 2025 to present our work - Interactive incremental learning of generalizable skills with local trajectory modulation. 🦾 Feel free to pass by to see my talk and chat with me at my poster. 💬 Robotic Imitation Learning 4 🗓️ Wed, Oct 22· 5:10PM 📍 Room 311 B
Image from Markus Knauer (@KnauerMarkus)
1
2
105
Paper: arxiv.org/abs/2409.05655
Interactive incremental learning of generalizable skills with...

Interactive incremental learning of generalizable skills with...

The problem of generalization in learning from demonstration (LfD) has received considerable attention over the years, particularly within the context of movement primitives, where a number of...

arxiv.org
1
22
Check out our paper presented at #ICRA2025 How can robotic systems articulate truthful answers about their internal knowledge in natural language? 🤖 📅 Presentation: May 20th, 2025, at 16:45 EDT in Room A314 📍 Poster session: Immediately following the talks
Image from Markus Knauer (@KnauerMarkus)
Image from Markus Knauer (@KnauerMarkus)
1
1
2
91
Paper link: elib.dlr.de/214144/
19
🚀 Exciting news! Our work has been published in IEEE 𝘙𝘰𝘣𝘰𝘵𝘪𝘤𝘴 𝘢𝘯𝘥 𝘈𝘶𝘵𝘰𝘮𝘢𝘵𝘪𝘰𝘯 𝘓𝘦𝘵𝘵𝘦𝘳𝘴 (𝘙𝘈-𝘓). See links in comments.
2
1
2
93
#robotics #research #interactiveLearning #imitationLearning #machineLearning #IEEE #RAL #IROS #FutureManufacturing #INVERSE #DLR
1
40
GitHub: github.com/DLR-RM/interactiv… ArXiv Paper: arxiv.org/abs/2409.05655 IEEE Explore: ieeexplore.ieee.org/document… YouTube: youtube.com/watch?v=nqigz0l1…
GitHub - DLR-RM/interactive-incremental-learning: Research code for the RA-L paper: Interactive...

GitHub - DLR-RM/interactive-incremental-learning: Research code for the RA-L paper: Interactive...

Research code for the RA-L paper: Interactive Incremental Learning of Generalizable Skills with Local Trajectory Modulation - DLR-RM/interactive-incremental-learning

github.com
1
54
Let’s meet at #CoRL in Munich :) We are presenting our approach about interactive incremental learning. If you are interested see the link in the comments or ask me directly:)
2
1
4
347
Part 2
1
36
Load more