EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

simDP: Sim-to-Real Transfer with Shared Action Spaces

Chanhyuk Jung, Jongbin Choi, Sungkeun Yoo iD, Byoung Chul Ko iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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

diffusion policyreal-world roboticsrobotic manipulationshared action spacesim-to-real

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}
}
Kostenlos starten →