Daniel Honerkamp

Daniel Honerkamp

PhD Student in Reinforcement Learning and Robotics

Embodied AI in Unknown and Open Worlds

I am a PhD student at the ELLIS Robot Learning Lab at the University of Freiburg. My research interests are focused on reinforcement learning, embodied AI and robotics. In my work, I enable mobile manipulation in unknown and unstructured environments. Much more broadly I am interested in all topics surrounding motion generation, autonomy and machine learning in unknown and open worlds.

In the past I have worked across all aspects of autonomous agents and their environments. After studying economics and working in econometric forecasting at the Swiss Central Bank, I graduated from the MSc Computational Statistics and Machine Learning at University College London. I then designed novel decentralised environments and consensus protocols before I flipped the coin and started to optimize agents’ behaviours within an environment during my PhD.

Publications

Task-Driven Co-Design of Mobile Manipulators, Raphael Schneider*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada, arXiv preprint arXiv:2412.16635, 2024.

Whole‑Body Teleoperation for Mobile Manipulation at Zero Added Cost, Daniel Honerkamp*, Harsh Mahesheka*, Jan Ole Hartz, Tim Welschehold, Abhinav Valada, IEEE Robotics and Automation Letters (RA‑L), 2025.

Language‑Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation, Daniel Honerkamp*, Martin Büchner*, Fabien Despinoy, Tim Welschehold, Abhinav Valada, IEEE Robotics and Automation Letters (RA‑L), 2024.

Recent Trends in Insect and Robot Navigation through the Lens of Reinforcement Learning, Stephan Lochner, Daniel Honerkamp, Abhinav Valada, Andrew D Straw, Frontiers in Computational Neuroscience, 2024.

Perception Matters: Enhancing Embodied AI with Uncertainty‑Aware Semantic Segmentation, Sai Prasanna*, Daniel Honerkamp*, Kshitij Sirohi*, Tim Welschehold, Wolfram Burgard, Abhinav Valada, Robotics Research, 2024.

N2M2: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments, Daniel Honerkamp, Tim Welschehold, Abhinav Valada, IEEE Transactions on Robotics (T‑RO), 2023.

Learning Hierarchical Interactive Multi‑Object Search for Mobile Manipulation, Fabian Schmalstieg*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada, IEEE Robotics and Automation Letters (RA‑L), 2023.

Catch Me if You Hear Me: Audio‑Visual Navigation in Complex Unmapped Environments With Moving Sounds, Abdelrahman Younes*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada, IEEE Robotics and Automation Letters (RA‑L), 2023.

Learning Long‑Horizon Robot Exploration Strategies for Multi‑Object Search in Continuous Action Spaces, Fabian Schmalstieg*, Daniel Honerkamp*, Tim Welschehold, Abhinav Valada, Robotics Research, 2022.

Active Particle Filter Networks: Efficient Active Localization in Continuous Action Spaces and Large Maps, Daniel Honerkamp, Suresh Guttikonda, Abhinav Valada, IROS Workshop on Probabilistic Robotics in the Age of Deep Learning, 2022.

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

Democratising blockchain: A minimal agency consensus model, Marcin Abram, Daniel Honerkamp, Jon Ward, Jin‑Mann Wong, Proceedings of Tokenomics International Conference on Blockchain Economics, Security and Protocols, 2019.

Awards