I’m Valentin! I am a Postdoc at the Computational Robotics Lab at ETH. I am working on real-world multi-agent task and motion planning, and am interested in how to deal with uncertainty, and how to get robots to be adaptive to changing circumstances.
I am always looking for good students - please reach out if you are interested in working with me!
Previously, I was in Marc Toussaint’s LIS group at TU Berlin, working on task and motion planning (TAMP) using optimization techniques, in addition to sampling based planners, with inspiration from control theory. I was associated with IntCDC, and was involved in several projects at the intersection of robotics and architecture.
In 2021, I (virtually) visited Jon Gammell’s ESP lab at the University of Oxford.
Generally, I like making robotics code go fast. Most of the time, the code I am looking at has strong relations to control systems, optimization, trajectory planning, or numerical methods. Before taking on my current position, I have been a mechanical engineering student at ETH Zurich, and have focussed on robotics, systems and control. I did a few internships at various companies (notably Amazon and BCG Gamma), and I was a PhD resident at intrinsic.ai working in the motion and controls team.
I like cycling, used to row competitively, like all kinds of other sports, and to my friends delight I am an avid cook.
I have an open list of ideas for which I am looking for collaborators (external pressure to complete something!) here. Contact me if anything catches your interest:
v [at] vhartmann [dot] com
for side-projects, valentin [dot] hartmann [at] inf [dot] ethz [dot] ch
for more academic chatter.
Publications
Also see my Google Scholar Profile here.
Preprints/Under Review
- iDb-A*: Iterative Search and Optimization for Optimal Kinodynamic Motion Planning, Joaquim Ortiz-Haro, Wolfgang Hoenig, Valentin N. Hartmann, Marc Toussaint, [arxiv], [code], [video]
Journals
- Long-Horizon Multi-Robot Rearrangement Planning for Construction Assembly, Valentin N. Hartmann, Andreas Orthey, Danny Driess, Ozgur S. Oguz, Marc Toussaint. IEEE T-RO 2022. [arxiv], [youtube], [paper]
- Leveraging Building Material as Part of the In-Plane Robotic Kinematic System for Collective Construction, Samuel Leder, H. Kim, Ozgur S. Oguz, Nicolas Kubail Kalousdian, Valentin N. Hartmann, Achim Menges, Marc Toussaint, Metin Sitti. Advanced Science 2022[paper]
- Learning Robotic Manipulation of Natural Materials with Variable Properties for Construction Tasks, Nicolas Kubail Kalousdian, Grzegorz Łochnicki, Valentin N. Hartmann, Samuel Leder, Ozgur S. Oguz, Achim Menges, Marc Toussaint, IEEE Robotics and Automation Letters (RA-L) 2022 [paper]
Conferences
- iDb-RRT: Sampling-based Kinodynamic Motion Planning with Motion Primitives and Trajectory Optimization, Joaquim Ortiz-Haro, Wolfgang Hönig, Valentin N. Hartmann, Marc Toussaint, and Ludovic Righetti, IROS 2024 [arxiv], [code], [video]
- Effort Level Search in Infinite Completion Trees with Application to Task-and-Motion Planning, Marc Toussaint, Joaquim Ortiz-Haro, Valentin N. Hartmann, Erez Karpas, Wolfgang Hönig, ICRA24
- Efficient Path Planning In Manipulation Planning Problems by Actively Reusing Validation Effort, Valentin N. Hartmann, Joaquim Ortiz-Haro, Marc Toussaint. International Conference on Intelligent Robots and Systems (IROS) 2023 [arxiv]
- Effort Informed Roadmaps (EIRM*): Efficient Asymptotically Optimal Multiquery Planning by Actively Reusing Validation Effort, Valentin N. Hartmann, Marlin P. Strub, Marc Toussaint, Jonathan D. Gammell. ISRR 2022. [arxiv], [youtube], [springer]
- ST-RRT*: Asymptotically-Optimal Bidirectional Motion Planning through Space-Time, Francesco Grothe, Valentin N. Hartmann, Andreas Orthey, Marc Toussaint, ICRA 2022, [arXiv]
- Learning Efficient Constraint Graph Sampling for Robotic Sequential Manipulation, Joaquim Ortiz-Haro, Valentin N. Hartmann, Ozgur S. Oguz, Marc Toussaint, ICRA 2021 [arxiv], [youtube]
- Self-supervised Learning of Scene-Graph Representations for Solving Sequential Manipulation Problems, Son-Tung Nguyen, Ozgur S. Oguz, Valentin N. Hartmann, Marc Toussaint, Conference on Robot Learning (CoRL) 2020 [paper], [youtube]
- Robust task and motion planning for long-horizon architectural construction planning, Valentin N. Hartmann, Ozgur S. Oguz, Danny Driess, Marc Toussaint and Achim Menges, International Conference on Intelligent Robots and Systems (IROS) 2020, [arXiv], [short video], [talk]
Workshops
- TAPAS: A Dataset for Task Assignment and Planning for Multi Agent Systems, Miguel Zamora, Valentin N. Hartmann, Stelian Coros, Workshop for Data Generation for Robotics at Robotics, Science and Systems ‘24
- Towards computing low-makespan solutions for multi-arm multi-task planning problems, Valentin N. Hartmann, Marc Toussaint. Workshop for Planning and Robotics (PlanRob), International Conference on Automated Planning and Scheduling (ICAPS), 2023 [arxiv], [blog]
- Planner Development Tools (PDT): Reproducible experiments and statistical analysis for developing and testing motion planners, Jonathan D. Gammell, Marlin P. Strub, Valentin N. Hartmann. Proceedings of the Workshop on Evaluating Motion Planning Performance (EMPP), International Conference on Intelligent Robots and Systems (IROS) 2022. [paper]
- Planning Planning: The Path Planner as a Finite State Machine, Valentin N. Hartmann, Ozgur S. Oguz, and Marc Toussaint. Workshop for Planning and Robotics (PlanRob), International Conference on Automated Planning and Scheduling (ICAPS), 2020. [talk], [paper]
- Co-Design in Architecture: A Modular Material-Robot Kinematic Construction System, Samuel Leder, HyunGyu Kim, Ozgur S. Oguz, Valentin N. Hartmann, Marc Toussaint, Achim Menges, Metin Sitti, Proceedings of Workshop on Construction and Architecture Robotics at IROS 2020. [paper]