Mitigating Catastrophic Forgetting in Robotic Waste Sorting: A Continual Learning Framework with Dynamic Experience Replay
Proceedings of the AAAI Symposium Series · 23.06.2026 · 9 (1) · 77-82
DOI: 10.1609/aaaiss.v9i1.42908 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.06.2026. Verfasst von Vlad Licaret und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Efficient sorting of critical waste materials (e.g., rare-earth elements, specific plastics, nuclear components) is essential for resource recovery and environmental safety. Deep learning models excel in visual-based sorting but fail to adapt to evolving waste streams without catastrophic forgetting of previously learned knowledge. This paper presents a continual learning framework for robotic waste sorting using classical experience replay. Our approach maintains a balanced memory buffer with reservoir sampling, enabling sequential learning of new material categories while preserving accuracy on previously encountered ones. Experiments on a curated dataset of critical waste materials demonstrate that our method reduces average forgetting compared to fine-tuning baselines and maintains sorting accuracy above 29% on old tasks while integrating new classes with minimal additional data. This work provides a pathway toward adaptive and sustainable waste management systems capable of lifelong operation in dynamic industrial environments.
Zitieren
APA
Licaret, V., Djenouri, Y., Jochemsen, A., & Belbachir, A. N. (2026). Mitigating Catastrophic Forgetting in Robotic Waste Sorting: A Continual Learning Framework with Dynamic Experience Replay. Proceedings of the AAAI Symposium Series, 9(1), 77-82. https://doi.org/10.1609/aaaiss.v9i1.42908
Vancouver
Licaret V, Djenouri Y, Jochemsen A, Belbachir AN. Mitigating Catastrophic Forgetting in Robotic Waste Sorting: A Continual Learning Framework with Dynamic Experience Replay. Proceedings of the AAAI Symposium Series. 2026;9(1):77-82. doi:10.1609/aaaiss.v9i1.42908
BibTeX
@article{Licaret2026,
author = {Licaret, Vlad and Djenouri, Youcef and Jochemsen, Arnoud and Belbachir, Ahmed Nabil},
title = {Mitigating Catastrophic Forgetting in Robotic Waste Sorting: A Continual Learning Framework with Dynamic Experience Replay},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {9},
number = {1},
pages = {77--82},
doi = {10.1609/aaaiss.v9i1.42908}
}
EUVIMED