Daniel Honerkamp

	PhD Student
	Postal address:	Albert-Ludwigs-Universität Freiburg Technische Fakultät Robot Learning Lab Georges-Köhler-Allee 080 D-79110 Freiburg i. Br., Germany
	Office:	Building 80, 01-23
	Email:	honerkamp@cs.uni-freiburg.de
	Phone:	+49 761 203-8010

About me

I am a PhD student in the Robot Learning Lab at the University of Freiburg in Germany.

My research aims to address the challenges in applying reinforcement learning to real world systems. This includes work around learning skills, representation learning, sample efficiency and self-supervision. I am also very interested in multi-disciplinary connections, such as with mechanism design and multi-agent systems.

Background

05/2020 - current: Ph.D. Student in the Robot Learning Lab, University of Freiburg
10/2018 - 04/2020: Machine Learning Engineer at Fetch.ai, Cambridge UK
10/2017 - 09/2018: M.Sc. Computational Statistics and Machine Learning, University College London
10/2013 - 07/2016: B.A. Economics, University of Zurich

Research Interests

Reinforcement Learning
Self-supervised Learning
Embodied AI

Current Research Projects

OpenDR - Open Deep learning toolkit for Robotics

Publications

Daniel Honerkamp, Tim Welschehold, Abhinav Valada,
N2M2:Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments
arXiv preprint arXiv:2206.08737, 2022.
Download Video Demo BibTeX

@article{honerkamp22n2m2,
	  title={N2M2:Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments},
	  author={Honerkamp, Daniel and Welschehold, Tim and Valada, Abhinav},
	  journal={arXiv preprint arXiv:2206.08737},
	  year={2022}
}

Abdelrahman Younes, Daniel Honerkamp, Tim Welschehold, Abhinav Valada,
SoundSpaces Challenge 2022 - 2nd Place
Conference on Computer Vision and Pattern Recognition (CVPR) Embodied AI Workshop, 2022.
Challenge

Fabian Schmalstieg*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada,
Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spaces
ArXiv preprint, 2022.
Download Demo BibTeX
@misc{https://doi.org/10.48550/arxiv.2205.11384, doi = {10.48550/ARXIV.2205.11384}, url = {https://arxiv.org/abs/2205.11384}, author = {Schmalstieg, F. and Honerkamp, D. and Welschehold, T. and Valada, A.}, keywords = {Robotics (cs.RO), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spaces}, publisher = {arXiv}, year = {2022}, } }

Abdelrahman Younes*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada,
Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds
ArXiv preprint, 2021.
Download BibTeX
@misc{https://doi.org/10.48550/arxiv.2111.14843, doi = {10.48550/ARXIV.2111.14843}, url = {https://arxiv.org/abs/2111.14843}, author = {Younes, Abdelrahman and Honerkamp, Daniel and Welschehold, Tim and Valada, Abhinav}, title = {Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds}, publisher = {arXiv}, year = {2021}, }

Abdelrahman Younes, Daniel Honerkamp, Tim Welschehold, Abhinav Valada,
SoundSpaces Challenge 2021 - 1st Place
Conference on Computer Vision and Pattern Recognition (CVPR) Embodied AI Workshop, 2021.
Video Challenge

Daniel Honerkamp, Tim Welschehold, Abhinav Valada,
Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning
IEEE Robotics and Automation Letters (RA-L), 2021.
Download Video Demo BibTeX

@article{honerkamp2021learning,
  title={Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning},
  author={Honerkamp, Daniel and Welschehold, Tim and Valada, Abhinav},
  journal={IEEE Robotics and Automation Letters (RA-L)},
  year={2021}
}

Marcin Abram, Daniel Honerkamp Jonathan Ward, Jin-Mann Wong
Democratising blockchain: A minimal agency consensus model
International Conference on Blockchain Economics, Security and Protocols (Tokenomics), Paris, 2019.
Download BibTeX

@misc{abram2020democratising,
      title={Democratising blockchain: A minimal agency consensus model}, 
      author={Marcin Abram and David Galindo and Daniel Honerkamp and Jonathan Ward and Jin-Mann Wong},
      year={2020},
      eprint={2006.05390},
      archivePrefix={arXiv},
      primaryClass={cs.CR}
}

Teaching

Seminars

Co-organizer, Deep Learning for Autonomous Systems Seminar, University of Freiburg, WS 2020/21
Co-organizer, Deep Learning Lab, University of Freiburg, SS 2020
Co-organizer, Self-Supervised Learning Seminar, University of Freiburg, SS 2020

Current Students

Hierarchical mobile manipulation, F. Schmalstieg, Master Thesis

Past Students

Deep active localization in continuous action spaces and realistic scenes, 2021, Suresh Guttikonda, Master Project
Dynamical Audio-Visual Navigation: Catching Unheard Moving Sound Sources in Unmapped 3D Environments, 2021, Abdelrahman Younes, Master Thesis (together with Tim Welschehold)
Reinforcement Learning for Indoor Multi-Object Exploration, 2022, F. Schmalstieg, Master Project (together with Tim Welschehold)
Model-Free RL for Robot Manipulation: Avoiding Configuration Jumps and Overestimation, 2022, A. Khalid, Master Project (together with Tim Welschehold)