EUVIMEDEUVIMED entdecken
Crossref

Repair2Skill: A Vision–Language–Action Framework for Robotic Furniture Repair

Mukesh Mani Tripathi, Hunag Xin, Qingqing Li

Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 109-117

DOI: 10.1609/aaaiss.v8i1.42525 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Mukesh Mani Tripathi und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Repair tasks differ fundamentally from robotic assembly, requiring fault localization, reverse dependency reasoning, and safe interaction with structurally degraded objects. While recent vision-language models have shown promise for high-level task reasoning, applying them to repair scenarios demands careful integration with perception, dependency modeling, and execution constraints. This paper presents Repair2Skill, a vision–language–action framework for robotic furniture repair that focuses on repair planning and simulation-based execution validation. The system detects damaged furniture components using a lightweight SSDLite-MobileNetV3 detector trained on procedurally generated synthetic damage data, constructs repair-oriented dependency graphs, and generates structured repair plans using a constrained large language model. Repair plans are restricted to a fixed action vocabulary and strict JSON schema to ensure deterministic parsing and feasibility. Generated plans are validated and visualized in a PyBullet simulation environment using kinematic action primitives, enabling interpretable verification of action ordering and dependency resolution without contact-rich physical manipulation. Experimental results demonstrate reliable part-damage association, achieving 76.8% mAP on real images, 100% valid repair plan generation under strict constraints, and stable simulation based validation across diverse repair scenarios. These results suggest that lightweight, constrained vision-language pipelines can support autonomous repair planning in bounded domains and provide a foundation for future work on physically grounded robotic repair.

Zitieren

APA

Tripathi, M. M., Xin, H., & Li, Q. (2026). Repair2Skill: A Vision–Language–Action Framework for Robotic Furniture Repair. Proceedings of the AAAI Symposium Series, 8(1), 109-117. https://doi.org/10.1609/aaaiss.v8i1.42525

Vancouver

Tripathi MM, Xin H, Li Q. Repair2Skill: A Vision–Language–Action Framework for Robotic Furniture Repair. Proceedings of the AAAI Symposium Series. 2026;8(1):109-117. doi:10.1609/aaaiss.v8i1.42525

BibTeX
@article{Tripathi2026,
  author = {Tripathi, Mukesh Mani and Xin, Hunag and Li, Qingqing},
  title = {Repair2Skill: A Vision–Language–Action Framework for Robotic Furniture Repair},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {109--117},
  doi = {10.1609/aaaiss.v8i1.42525}
}
Kostenlos starten →