simDP: Sim-to-Real Transfer with Shared Action Spaces
Sensors · 27.06.2026 · 26 (13) · 4079
DOI: 10.3390/s26134079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 27.06.2026. Verfasst von Chanhyuk Jung und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Keimyung University, Daegu 42601, Republic of Korea. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Education of the Republic of Korea.
Abstract (Originalsprache)
In this paper, we propose simDP, a sim-to-real transfer framework that enables diffusion policies trained in simulations for the efficient deployment on real-world robots. The key idea is to reduce the sim-to-real gap by aligning the action and observation spaces between simulation and reality. Specifically, we reformulate the action space using end-effector pose and binary gripper state, which can be shared between simulated and physical robots. In addition, we use camera-based visual observations as the primary sensing modality in both domains and train a real-world observation encoder to align with the latent representation learned in simulation. This design allows the action decoder trained in simulation to be reused in the real-world with minimal modification. We evaluated simDP on object manipulation tasks derived from the MimicGen benchmark and show that a simulation-trained diffusion decoder, when combined with a real-world adapted observation encoder, achieves task completion performance similar to and in some cases better than diffusion policies trained only on limited real-world data. These results, obtained across four manipulation tasks in a calibrated real-world transfer setting, suggest that reusing a simulation-trained action decoder with lightweight real-world encoder adaptation provides an effective strategy for controlled sim-to-real transfer, while broader evaluation across diverse tasks, environments, and robot embodiments remains an important direction for future work.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Keimyung University, Daegu 42601, Republic of Korea.
- Department of Robot Engineering, Keimyung University, Daegu 42601, Republic of Korea.
ORCID-Profile: Sungkeun Yoo, Byoung Chul Ko
Förderung
- National Research Foundation of Korea
- Ministry of Education of the Republic of Korea
Zitieren
APA
Jung, C., Choi, J., Yoo, S., & Ko, B. C. (2026). simDP: Sim-to-Real Transfer with Shared Action Spaces. Sensors, 26(13), 4079. https://doi.org/10.3390/s26134079
Vancouver
Jung C, Choi J, Yoo S, Ko BC. simDP: Sim-to-Real Transfer with Shared Action Spaces. Sensors. 2026;26(13):4079. doi:10.3390/s26134079
BibTeX
@article{Jung2026,
author = {Jung, Chanhyuk and Choi, Jongbin and Yoo, Sungkeun and Ko, Byoung Chul},
title = {simDP: Sim-to-Real Transfer with Shared Action Spaces},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {4079},
doi = {10.3390/s26134079}
}
EUVIMED