Martin Büchner

	PhD Student
	Postal address:	Albert-Ludwigs-Universität Freiburg Technische Fakultät Robot Learning Lab Georges-Köhler-Allee 080 D-79110 Freiburg i. Br., Germany
	Office:	080-00-022
	Email:	buechner@cs.uni-freiburg.de

About me

10/21 - current: Ph.D. Student in the Robot Learning Lab, University of Freiburg
10/18 - 04/21: Scholarship Student, BMW Autonomous Driving, Munich
10/18 - 09/21: M.Sc. in Robotics, Cognition, Intelligence, Technical University of Munich (TUM)
08/19 - 12/19: Visiting Intern, Lab for Autonomous Robotics Research, Seoul National University (SNU), Korea
09/16 - 06/17: Exchange Student in Mechanical Engineering, Purdue University, USA
10/14 - 09/18: B.Sc. in Mechanical Engineering, Karlsruhe Institute of Technology (KIT)

Research Interests

Learning on Graph Structures
3D Scene Graphs, Vision-Language Navigation & Manipulation, Open-Vocabulary Perception
State Estimation for Robotics

Teaching

TA, Advanced DL: Graph Neural Networks, Summer Term 2024
TA, FreiCAR: Practical Autonomous Driving, Winter Term 2023
TA, Seminar: Learning with Limited Supervision, Summer Term 2023
TA, FreiCAR: Practical Autonomous Driving, Winter Term 2022
TA, Seminar: Learning with Limited Supervision Summer Term 2022
TA, FreiCAR: Practical Autonomous Driving, Summer term 2022

Students

Elias Greve: Collaborative Panoptic Mapping (Oct 22)
Amrutha Venkatesan: 3D Multi-Agent Multi-Object Tracking (May 22)
Abdelrhman Werby: Hierarchical Open-Vocabulary Scene Graphs (Jun 23)
Simon Dorer: Learning Lane Graphs Using Transformers from Aerial Imagery (Oct 23)
Rishabh Verma: 3D Scene Graph Filtering for Robotic Planning Using Graph Neural Networks (Nov 23)
Yusuf Salcan: Grasping Pairs of Points Using Graph Neural Networks (Apr 24)
Tim Steinke: Collaborative Open-Vocabulary 3D Scene Graphs for Automated Driving
Amrutha Venkatesan: Multi-Modal Data Association in 3D Multi-Object Tracking using Graph Transformers (Mercedes Benz AG)
Abdelrhman Werby: TBA
Lennart Koenig: TBA

Publications

View all my publications on Google Scholar.

Christina Kassab, Sacha Morin, Martin Büchner, Matías Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon,
OpenLex3D: A New Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
arXiv preprint arXiv:2503.19764, 2025.
Download Website BibTeX

@article{kassab2025openlex3d,
      author={Kassab, Christina and Morin, Sacha and Büchner, Martin and Mattamala, Matías and Gupta, Kumaraditya and Valada, Abhinav and Paull, Liam and Fallon, Maurice},
      title={OpenLex3D: A New Evaluation Benchmark for Open-Vocabulary 3D Scene Representations}, 
      journal={arXiv preprint arXiv:2503.19764},
      year={2025},
}

Tim Steinke*, Martin Büchner*, Niclas Vödisch*, Abhinav Valada,
Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Scene Understanding
arXiv preprint arXiv:2503.08474, 2025.
Download Website Video BibTeX

@article{steinke2025curbosg,
  author={Steinke, Tim and Büchner, Martin and Vödisch, Niclas and Valada, Abhinav},
  title={Collaborative Dynamic 3D Scene Graphs for Open-Vocabulary Urban Scene Understanding},
  journal={arXiv preprint arXiv:2503.08474},
  year={2025},
}

Christina Kassab, Matías Mattamala, Sacha Morin, Martin Büchner, Abhinav Valada, Liam Paull, Maurice Fallon,
The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs
arXiv preprint arXiv:2412.01539, 2024.
Download BibTeX

@article{kassab24ovsg,
      title={The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs},
      author={Kassab, Christina and Mattamala, Matías and Morin, Sacha and Büchner, Martin and Valada, Abhinav and Paull, Liam and Fallon, Maurice},
      journal={arXiv preprint arXiv:2412.01539},
      year={2024}
}

Martin Büchner*, Simon Dorer*, Abhinav Valada
Learning Lane Graphs from Aerial Imagery Using Transformers
RSS 2024 Workshop on Autonomous Vehicles Across Scales (AVAS)
Download BibTeX

@article{buechner24learning,
  title={Learning Lane Graphs from Aerial Imagery Using Transformers},
  author={Martin Büchner, Simon Dorer, and Abhinav Valada},
  journal={arXiv preprint arXiv:2407.05687},
  year={2024}
}

Abdelrhman Werby*, Chenguang Huang*, Martin Büchner* , Abhinav Valada, Wolfram Burgard
Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation
Robotics: Science and Systems (RSS), 2024.
ICRA 2024 Workshop on Vision and Language Models for Navigation and Manipulation (VLMNM)
Download Website BibTeX
```
@article{werby24hierarchical,
  title={Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation},
  author={Abdelrhman Werby, Chenguang Huang, Martin Büchner, Abhinav Valada, and Wolfram Burgard},
  journal={arXiv preprint arXiv:2403.17846},
  year={2024}
}
    
```
Daniel Honerkamp*, Martin Büchner*, Fabian Despinoy, Tim Welschehold, Abhinav Valada
Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation
IEEE Robotics and Automation Letters (RA-L), 2024.
Spotlight Talk: RSS 2024 1st Workshop on Semantic Reasoning and Goal Understanding in Robotics (SemRob)
Spotlight Talk: ICRA 2024 Workshop on Vision and Language Models for Navigation and Manipulation (VLMNM)
Download Website BibTeX
```
@article{honerkamp24language,
  title={Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation},
  author={Daniel Honerkamp, Martin Büchner, Fabien Despinoy, Tim Welschehold, and Abhinav Valada},
  journal={arXiv preprint arXiv:2403.08605},
  year={2024}
}
    
```

Elias Greve*, Martin Büchner*, Niclas Vödisch*, Wolfram Burgard, Abhinav Valada
Collaborative Dynamic 3D Scene Graphs for Automated Driving
IEEE International Conference on Robotics and Automation (ICRA), 2024 🇯🇵
Download Website BibTeX

@article{greve2023collaborative,
  title={Collaborative Dynamic 3D Scene Graphs for Automated Driving},
  author={Greve, Elias and B{\"u}chner, Martin and V{\"o}disch, Niclas and Burgard, Wolfram and Valada, Abhinav},
  journal={arXiv preprint arXiv:2309.06635},
  year={2023}
}

Max Argus*, Abhijeet Nayak*, Martin Büchner, Silvio Galesso, Abhinav Valada , Thomas Brox
Compositional Servoing by Recombining Demonstrations
IEEE International Conference on Robotics and Automation (ICRA), 2024 🇯🇵
Download Website BibTeX

@misc{argus2023compositional,
      title={Compositional Servoing by Recombining Demonstrations}, 
      author={Max Argus and Abhijeet Nayak and Martin Büchner and Silvio Galesso and Abhinav Valada and Thomas Brox},
      year={2023},
      eprint={2310.04271},
      archivePrefix={arXiv},
      primaryClass={cs.RO}
}

Raphael Trumpp*, Martin Büchner*, Abhinav Valada, Marco Caccamo
Efficient Learning of Urban Driving Policies Using Bird's-Eye-View Representations
IEEE Intelligent Transportation Systems Conference (ITSC), 2023
Download Website BibTeX

@article{trumpp2023efficient,
      title={Efficient Learning of Urban Driving Policies Using Bird's-Eye-View State Representations},
      author={Raphael Trumpp and Martin Büchner and Abhinav Valada and Marco Caccamo},
      year={2023},
      eprint={2305.19904},
      archivePrefix={arXiv},
      primaryClass={cs.RO}
    }

Martin Büchner*, Jannik Zürn*, Ion-George Todoran, Abhinav Valada, Wolfram Burgard
Learning and Aggregating Lane Graphs for Urban Automated Driving
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023.
Download Website BibTeX

@article{buchner2023learning,
  title={Learning and Aggregating Lane Graphs for Urban Automated Driving},
  author={B{\"u}chner, Martin and Z{\"u}rn, Jannik and Todoran, Ion-George and Valada, Abhinav and Burgard, Wolfram},
  journal={arXiv preprint arXiv:2302.06175},
  year={2023}
}

Martin Büchner, Abhinav Valada
3D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attention
IEEE Robotics and Automation Letters (RA-L), 2022 + IROS.
Download Website Video BibTeX

@article{buechner22batch3dmot,
	  title={3D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attention},
	  author={B{\"u}chner, Martin and Valada, Abhinav},
	  journal={arXiv preprint arXiv:2203.10926},
	  year={2022}
}

Ana Petrovska, Malte Neuss, Sebastian Bergemann, Martin Buechner, M. Ansab Shohab,
Smart Self-Adaptive Cyber-Physical Systems: How can Exploration and Learning Improve Performance in a Partially Observable Multi-Agent Context?
ADAPTIVE 2021: The Thirteenth International Conference on Adaptive and Self-Adaptive Systems and Applications, 2021.
Download