EUVIMEDEUVIMED entdecken
Crossref

Lifelong Language-Conditioned Robotic Manipulation Learning

Xudong Wang, Zebin Han, Zhiyu Liu, Gan Li, Jiahua Dong, Baichen Liu, Lianqing Liu, Zhi Han

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (22) · 18629-18637

DOI: 10.1609/aaai.v40i22.38930 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xudong Wang und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional language-conditioned manipulation agent adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a novel robotic manipulation framework designed to continually learn multiple skills while reducing catastrophic forgetting of old skills. Specifically, we propose a Manipulation Skills Adaptation to retain the old skills knowledge while inheriting the shared knowledge between new and old skills to facilitate learning of new skills. Meanwhile, we perform the singular value decomposition on the diverse skill instructions to obtain common skill semantic subspace projection matrices, thereby recording the essential semantic space of skills. To achieve forget-less and generalization manipulation, we propose a Skills Specialization Aggregation to compute inter-skills similarity in skill semantic subspaces, achieving aggregation of the previously learned skill knowledge for any new or unknown skill. Extensive simulator and real-world experiments demonstrate the effectiveness and superiority of our SkillsCrafter.

Zitieren

APA

Wang, X., Han, Z., Liu, Z., Li, G., Dong, J., Liu, B., Liu, L., & Han, Z. (2026). Lifelong Language-Conditioned Robotic Manipulation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(22), 18629-18637. https://doi.org/10.1609/aaai.v40i22.38930

Vancouver

Wang X, Han Z, Liu Z, Li G, Dong J, Liu B, et al. Lifelong Language-Conditioned Robotic Manipulation Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(22):18629-18637. doi:10.1609/aaai.v40i22.38930

BibTeX
@article{Wang2026,
  author = {Wang, Xudong and Han, Zebin and Liu, Zhiyu and Li, Gan and Dong, Jiahua and Liu, Baichen and Liu, Lianqing and Han, Zhi},
  title = {Lifelong Language-Conditioned Robotic Manipulation Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {22},
  pages = {18629--18637},
  doi = {10.1609/aaai.v40i22.38930}
}
Kostenlos starten →