Nico Bohlinger
Research Interests
Reinforcement Learning, Robotics, Morphology-aware and Multi-Embodiment Learning, Co-Design, Humanoids
Affiliation
TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
nico.bohlinger@tu-darmstadt.de
Room E327, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-25380
Nico Bohlinger joined the Intelligent Autonomous System lab on July 15, 2023, as a PhD student.
Nico is working on learning embodied intelligence by applying Reinforcement Learning (RL) at scale to robotics.
Besides many side projects, his core work focuses on:
- The Unified Robot Morphology Architecture (URMA), a fully morphology-aware neural network architecture, to learn a single policy to control any legged robot embodiment.
This approach shows embodiment scaling laws and can be scaled to millions of embodiments.
- Learning natural and omnidirectional locomotion in just 8 minutes with efficient off-policy RL directly on a real quadruped robot.
- Currently: Training VLAs for Humanoid Loco-Manipulation by combining VLMs with online RL in large scale randomized simulation environments.
His main robot platforms are currently the Unitree H1, Unitree G1 and Booster T1 humanoids and the Unitree Go2 and MAB Silver Badger quadrupeds.
Before he started his PhD, Nico obtained a bachelor's degree in Business Informatics from the Offenburg University of Applied Sciences and a master's degree in Bioinformatics from the Goethe University Frankfurt.
He was previously part of the RoboCup teams Magma and Sweaty in Offenburg and developed RL environments to learn complex soccer skills.
Furthermore, he is developing the research-focused RL framework RL-X.
Publications
Conferences
- Bohlinger, N.; Ai, B.; Dai, L.; Li, D.; Mu, T.; Wu, Z.; Fay, K.; Christensen, H.I.; Peters, J.; Su, H. (2025). Towards Embodiment Scaling Laws in Robot Locomotion, Conference on Robot Learning (CoRL).
- Aditya, D.; Huang, J.; Bohlinger, N.; Kicki, P.; Walas, Peters, J.; Luperto, M.; Tateo, D. (2025). Robust Localization, Mapping, and Navigation for Quadruped Robots, European Conference on Mobile Robots (ECMR).
- Bohlinger, N.; Kinzel, J.; Palenicek, D.; Antczak, L.; Peters, J. (2025). Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion, International Conference on Intelligent Robots and Systems (IROS).
- Bohlinger, N.; Stasica, M.; Bick, A.; Mohseni, O.; Fritzsche, J.; Hübler, C.; Peters, J.; Seyfarth, A. (2025). Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations, International Conference on Intelligent Robots and Systems (IROS).
- Bohlinger, N.; Peters, J. (2025). Massively Scaling Explicit Policy-conditioned Value Functions, Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2025). Morphology-Aware Legged Locomotion with Reinforcement Learning, German Robotics Conference (GRC).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion, Conference on Robot Learning (CoRL).
Workshops & Symposia
- Bohlinger, N.; Kicki, P.; Tateo, D.; Walas, K.; Peters, J. (2025). Evaluation of an Actuated Spine in Agile Quadruped Locomotion, IROS 2025 Workshop on Climbing Robotics.
- Bohlinger, N.; Peters, J. (2025). Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization, IROS 2025 Workshop on Foundation Models for Robotic Design.
- Bohlinger, N.; Peters, J. (2025). Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization, IROS 2025 Workshop on Challenges and Application Prospects for Reconfigurable Modular Robots.
- Bohlinger, N.; Peters, J. (2025). Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization, Humanoids 2025 Workshop on Sim-to-Real Transfer for Humanoid Robots.
- Bohlinger, N.; Kinzel, J.; Palenicek, D.; Antczak, L.; Peters, J. (2025). Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion, European Workshop on Reinforcement Learning (EWRL).
- Bohlinger, N.; Ai, B.; Dai, L.; Li, D.; Mu, T.; Wu, Z.; Fay, K.; Christensen, H.I.; Peters, J.; Su, H. (2025). Towards Embodiment Scaling Laws in Robot Locomotion, RSS 2025 Workshop on Robot Hardware-Aware Intelligence.
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2025). Learning Robot Locomotion for Multiple Embodiments, The 12th International Symposium on Adaptive Motion of Animals and Machines and 2nd LokoAssist Symposium (AMAM).
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion, CoRL 2024 Morphology-Aware Policy and Design Learning Workshop.
- Bohlinger, N.; Czechmanowski, G.; Krupka, M.; Kicki, P.; Walas, K.; Peters, J.; Tateo, D. (2024). One Policy to Run Them All: Towards an End-to-end Learning Approach to Multi-Embodiment Locomotion, RSS 2024 Workshop on Embodiment-Aware Robot Learning.
- Bohlinger, N.; Tateo, D.; Kicki, P.; Walas, K.; Peters, J. (2024). Benefits of an Actuated Spine in Agile Quadruped Locomotion, ICRA 2024 Workshop on Bio-inspired Robotics and Robotics for Biology.
- Bohlinger, N.; Dorer, K. (2023). RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup, RoboCup 2023: Robot World Cup XXVI, Springer-Verlag.
Others
- Bohlinger, N. (2023). Intrinsically Motivated Agents for Goal Discovery in High Dimensional State Spaces, Master Thesis.
- Bohlinger, N.; Braun, H.; Dorer, K.; Ehlers, L.; Huber, D.; Huber, H.; Glaser, S.; Schillings, R.; Scholz, J.; Wolffram, M. (2022). The magmaOffenburg 2022 RoboCup 3D Simulation Team.
Awards
- Best Poster Award: Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization @ IROS 2025 Workshop on Foundation Models for Robotic Design
Talks and Interviews
Supervised Theses and Projects
| Thesis/Project | Topic | Student(s) | Together with |
| M.Sc. Thesis | Adaptive Restart Distributions for Accelerating Reinforcement Learning | Michelle Shaia | Aryaman Reddi |
| M.Sc. Thesis | Embodiment Adaptive Control | Dichen Li @ UC San Diego | Bo Ai |
| M.Sc. Thesis | On-robot Deep Reinforcement Learning for Quadruped Locomotion | Jonathan Kinzel | Daniel Palenicek |
| M.Sc. Thesis | Gait Analysis of Quadruped Robots during Vertical Ground Perturbations | Arne Bick | Maximilian Stasica, Omid Mohseni |
| Robot Learning: Integrated Project | Large-scale Procedural Robot Generation | Nurhak Yalcin, Lukas Müller | |
| Robot Learning: Integrated Project | Learning Torque Control for Quadrupeds | Daniel Schmidt, Lina Gaumann | |
| Robot Learning: Integrated Project | Student-Teacher Learning for simulated Quadrupeds | Keagan Holmes, Oliver Griess, Oliver Grein | |
| Expert Project in Robot Learning | Deep Reinforcement Learning with the Unitree Go2 robot in MJX | Leon Magnus | Oleg Arenz |
| Humanoid Robotics Seminar | Reinforcement Learning for Humanoid Locomotion | Qiao Sun |
Others
- Reviewed for: ICRA (2024, 2025, 2026), IROS (2024, 2025), CoRL (2025), EWRL (2025), RA-L (2025), T-RO (2025), Science Robotics (2025)
- TA for: Robot Learning SS24, Probabilistic Methods in Computer Science WS24/25
- Organizer of: International Workshop of Intelligent Autonomous Learning Systems (IWIALS) 2025