Jan Peters

Short info

My research focusses on a better understanding of motor skill learning and execution in both man and machines. To accomplish this goal, I am interested both into endowing robots with new skills as well as to improve our understanding of human motor skills through computational models of learning and control. Thus, I am using methods from artificial intelligence to synthesize new machine learning algorithms and motor learning architectures to enable anthropomorphic robots to acquire new skills such as juggling, table tennis, grasping & manipulation, locomotion and many more. Similarly, I am interested at using similar machine learning for analysis of behavior from a cognitive science point of view to improve our understanding of human motor abailities, for example in human ball catching, human tactile manipulation or human table tennis. My long-term goal is to provide a unified framework for understanding motor control that enables us to take our robots out of the research and factory floors into human-inhabited environments.

Open Science

Böhm, A., Schneider, T., Belousov, B., Kshirsagar, A., Lin, L., Doerschner, K., ... & Peters, J. (2024).
What matters for active texture recognition with vision-based tactile sensors.
arXiv preprint 2403, 13701.

Chen, J., Kshirsagar, A., Heller, F., Andreu, M. G., Belousov, B., Schneider, T., Lin, L. P., Doerschner, K., Drewing, K., & Peters, J. (2025).
Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors.
arXiv preprint arXiv:2505.13231.

Helmut, E., Dziarski, L., Funk, N., Belousov, B., & Peters, J. (2024).
Learning force distribution estimation for the gelsight mini optical tactile sensor based on finite element analysis.
arXiv preprint arXiv: 2411.03315.

Kaidanov, O., Al-Hafez, F., Suvari, Y., Belousov, B., & Peters, J. (2024).
The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control.
arXiv preprint arXiv: 2411.01349.

Meser, M., Bhatt, A., Belousov, B., & Peters, J. (2024).
Mujoco mpc for humanoid control: Evaluation on humanoidbench.
arXiv preprint arXiv: 2408.00342.

Nguyen, D. H., Schneider, T., Duret, G., Kshirsagar, A., Belousov, B., & Peters, J. (2024).
TacEx: GelSight Tactile Simulation in Isaac Sim--Combining Soft-Body and Visuotactile Simulators.
arXiv preprint arXiv: 2411.04776.

Nonnengießer, F., Kshirsagar, A., Belousov, B., & Peters, J. (2025).
In-Hand Object Pose Estimation via Visual-Tactile Fusion.
arXiv preprint arXiv:2506.10787.

Palenicek, D., Gruner, T., Schneider, T., Böhm, A., Lenz, J., Pfenning, I., ... & Peters, J. (2024).
Learning tactile insertion in the real world.
arXiv preprint arXiv:. 2405.00383.

Palenicek, D., Vogt, F., & Peters, J. (2025).
Scaling CrossQ with Weight Normalization.
arXiv preprint arXiv: 2506.03758.

Straub, D., Niehues, T. F., Peters, J., & Rothkopf, C. A. (2024).
Inverse decision-making using neural amortized Bayesian actors.
arXiv preprint arXiv: 2409.03710.

Wiebe, F., Turcato, N., Libera, A. D., Choe, J. S. B., Choi, B., Faust, T. L., Peters, J., ... & Kumar, S. (2025).
Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd'AI Olympics with RealAIGym'Competition.
arXiv preprint arXiv: 2503.15290.

Articles

Böhm, A., Schneider, T., Belousov, B., Kshirsagar, A., Lin, L., Doerschner, K., ... & Peters, J. (2024).
What matters for active texture recognition with vision-based tactile sensors.
2024 IEEE International Conference on Robotics and Automation (ICRA), 15099-15105.

Göksu, Y., De Almeida Correia, A., Prasad, V., Kshirsagar, A., Koert, D., Peters, J., & Chalvatzaki, G. (2024).
Kinematically Constrained Human-like Bimanual Robot-to-Human Handovers.
Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 497-501.

Gu, S., Liu, P., Kshirsagar, A., Chen, G., Peters, J., & Knoll, A. (2024).
Roscom: Robust safe reinforcement learning on stochastic constraint manifolds.
IEEE Transactions on Automation Science and Engineering

Hahne, F., Prasad, V., Kshirsagar, A., Koert, D., Stock-Homburg, R. M., Peters, J., & Chalvatzaki, G. (2024).
Transition State Clustering for Interaction Segmentation and Learning.
Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 512-516.

Koosha, T.A., Hahne, F., Kshirsagar, A., Augustat, N., Melzig, C.A., Bremmer, F., Peters, J., & Endres, D.M. (2025).
Inferring Height-Induced Changes in Postural Control via Inverse Optimal Control.
Conference on Cognitive Computational Neuroscience (CCN).

Lin, L. P. Y., Böhm, A., Belousov, B., Kshirsagar, A., Schneider, T., Peters, J., Doerschner, K., & Drewing, K. (2024).
Task-Adapted Single-Finger Explorations of Complex Objects.
EuroHaptics

Prasad, V., Kshirsagar, A., Koert, D., Stock-Homburg, R., Peters, J., & Chalvatzaki, G. (2024).
Moveint: Mixture of variational experts for learning human–robot interactions from demonstrations.
IEEE Robotics and Automation Letters, 9(7), 6043-6050.

Prasad, V., Kshirsagar, A., Stock-Homburg, D. K. R., Peters, J., & Chalvatzaki, G. (2024).
MoVEInt: Mixture of Variational Experts for Learning Human-Robot Interactions from Demonstrations.
IEEE Robotics and Automation Letters.

Spartakov, R., Kshirsagar, A., Mühl, D., Schween, R., Endres, D. M., Bremmer, F., ... & Peters, J. (2024).
Balancing on the Edge: Review and Computational Framework on the Dynamics of Fear of Falling and Fear of Heights in Postural Control.
Proceedings of the Annual Meeting of the Cognitive Science Society (46).