EUVIMEDEUVIMED entdecken
Crossref

LUDO: Low-Latency Understanding of Deformable Objects Using Point Cloud Occupancy Functions (Abstract Reprint)

Pit Henrich, Franziska Mathis-Ullrich, Paul Maria Scheikl

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39869-39869

DOI: 10.1609/aaai.v40i47.41384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Pit Henrich und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately determining the shape of deformable objects and the location of their internal structures is crucial for medical tasks that require precise targeting, such as robotic biopsies. We introduce LUDO, a method for accurate low-latency understanding of deformable objects. LUDO reconstructs objects in their deformed state, including their internal structures, from a single-view point cloud observation in under 30 ms using occupancy networks. LUDO provides uncertainty estimates for its predictions. Additionally, it provides explainability by highlighting key features in its input observations. Both uncertainty and explainability are important for safety-critical applications such as surgery. We evaluate LUDO in real-world robotic experiments, achieving a success rate of 98.9% for puncturing various regions of interest (ROIs) inside deformable objects. We compare LUDO to a popular baseline and show its superior ROI localization accuracy, training time, and memory requirements. LUDO demonstrates the potential to interact with deformable objects without the need for deformable registration methods.

Zitieren

APA

Henrich, P., Mathis-Ullrich, F., & Scheikl, P. M. (2026). LUDO: Low-Latency Understanding of Deformable Objects Using Point Cloud Occupancy Functions (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39869-39869. https://doi.org/10.1609/aaai.v40i47.41384

Vancouver

Henrich P, Mathis-Ullrich F, Scheikl PM. LUDO: Low-Latency Understanding of Deformable Objects Using Point Cloud Occupancy Functions (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39869-39869. doi:10.1609/aaai.v40i47.41384

BibTeX
@article{Henrich2026,
  author = {Henrich, Pit and Mathis-Ullrich, Franziska and Scheikl, Paul Maria},
  title = {LUDO: Low-Latency Understanding of Deformable Objects Using Point Cloud Occupancy Functions (Abstract Reprint)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39869--39869},
  doi = {10.1609/aaai.v40i47.41384}
}
Kostenlos starten →