EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RG-RGD: Task-Triggered Small-Target RGB-D Depth Refinement for Robotic Laser Ablation

Bowen Si, Dayong Ning, Jiaoyi Hou, Yongjun Gong, Ming Yi, Fengrui Zhang, Zhilei Liu

Machines · 25.07.2026 · 14 (8) · 841

DOI: 10.3390/machines14080841 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 25.07.2026. Verfasst von Bowen Si und 6 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the Fundamental Research Funds for the Central Universities, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Robotic 3D manipulation of small targets, such as laser ablation of urban-tree fruit balls, requires locally reliable depth. Mainstream RGB-D depth-refinement methods usually optimize image-wide metrics, which can leave task-relevant regions under-resolved and limit their direct use in precision robotic operation. This paper presents residual-gated RGB-D depth refinement (RG-RGD), a task-triggered local depth-refinement framework that reallocates computation toward task-relevant 3D geometry after a candidate target has been selected. The method contains three coupled designs: a self-play benefit-driven foveation mechanism that focuses network capacity on regions where refinement reduces geometric residuals; residual prediction with Bayesian measurement fusion that anchors predictions to available raw observations; and inertial measurement unit (IMU)-conditioned self-supervised training that improves inter-frame view consistency. Evaluated on the Visual Odometry with Inertial and Depth (VOID) benchmark, RG-RGD obtains competitive standard depth-completion metrics, including a mean absolute error (MAE) of 24.95 mm and an inverse mean absolute error (iMAE) of 10.85. On self-collected London plane fruit-ball sequences, the method reduces region-of-interest geometric error more strongly than full-image error. A qualitative demonstrative laser-ablation use case illustrates how refined local geometry can drive physical branch filtering, cutting-point selection, and gimbal-based execution. The results support task-triggered local depth refinement as a practical perception component for robotic manipulation.

Förderung

  • National Natural Science Foundation of China
  • the Fundamental Research Funds for the Central Universities
  • National Key Research and Development Program of China

Zitieren

APA

Si, B., Ning, D., Hou, J., Gong, Y., Yi, M., Zhang, F., & Liu, Z. (2026). RG-RGD: Task-Triggered Small-Target RGB-D Depth Refinement for Robotic Laser Ablation. Machines, 14(8), 841. https://doi.org/10.3390/machines14080841

Vancouver

Si B, Ning D, Hou J, Gong Y, Yi M, Zhang F, et al. RG-RGD: Task-Triggered Small-Target RGB-D Depth Refinement for Robotic Laser Ablation. Machines. 2026;14(8):841. doi:10.3390/machines14080841

BibTeX
@article{Si2026,
  author = {Si, Bowen and Ning, Dayong and Hou, Jiaoyi and Gong, Yongjun and Yi, Ming and Zhang, Fengrui and Liu, Zhilei},
  title = {RG-RGD: Task-Triggered Small-Target RGB-D Depth Refinement for Robotic Laser Ablation},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {841},
  doi = {10.3390/machines14080841}
}
Kostenlos starten →