{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:38:05Z","timestamp":1760575085868,"version":"build-2065373602"},"reference-count":32,"publisher":"Emerald","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,16]]},"abstract":"<jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>This paper aims to propose a domain-incremental learning method for weld seam tracking robots, to address the catastrophic forgetting problem that arises when seam samples are sequentially introduced, especially under production demands characterized by small batches and multiple varieties.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design\/methodology\/approach<\/jats:title>\n                  <jats:p>The weld seam tracking robot uses a light-weight semantic segmentation network, ENetx74, to extract laser stripes and uses the efficient convolution operator, independent of deep learning, to locate feature points. The proposed method uses distillation with old samples for rehearsal to retrain ENetx74 on new data sets while maintaining its performance on old ones and a memory blur strategy to reduce storage costs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>Compared to the state-of-the-art methods, the Backward Transfer, which measures the model\u2019s performance on old tasks after learning new ones, increased by 34.8%\u201371.7%, while storage costs dropped by 48.45%, demonstrating the method\u2019s effectiveness in achieving stronger generalization with less storage cost. Furthermore, seam tracking experimental results show mean tracking errors below 0.3 mm and maximum tracking errors smaller than those of the baseline, effectively mitigating the forgetting problem.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Originality\/value<\/jats:title>\n                  <jats:p>This paper proposes a domain-incremental learning method based on rehearsal for weld seam tracking robot, combining a memory blur strategy to reduce storage cost. Guided by the generalization error bound based on Vapnik\u2013Chervonenkis dimension, the reduction in storage costs facilitates increasing the number of old samples used for rehearsal, enhancing the robot\u2019s ability to generalize.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1108\/ir-11-2024-0528","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T07:48:39Z","timestamp":1741679319000},"page":"792-802","source":"Crossref","is-referenced-by-count":0,"title":["A rehearsal-based domain-incremental learning method for weld seam tracking robot to enhance generalization"],"prefix":"10.1108","volume":"52","author":[{"given":"Yangzhuo","family":"Yan","sequence":"first","affiliation":[{"name":"South China University of Technology School of Mechanical and Automative Engineering, , Guangzhou,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbiao","family":"Zou","sequence":"additional","affiliation":[{"name":"South China University of Technology School of Mechanical and Automative Engineering, , Guangzhou,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"key":"2025101507172540500_ref001","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/B978-0-12-821049-9.00005-8","volume-title":"Microscope Image Processing","author":"Castleman","year":"2023","edition":"2nd ed"},{"key":"2025101507172540500_ref002","first-page":"9230","article-title":"Modeling the background for incremental learning in semantic segmentation","author":"Cermelli","year":"2020"},{"key":"2025101507172540500_ref003","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01252-6_33","article-title":"Riemannian walk for incremental learning: understanding forgetting and intransigence","author":"Chaudhry","year":"2018"},{"key":"2025101507172540500_ref004","first-page":"4039","article-title":"Plop: learning without forgetting for continual semantic segmentation","author":"Douillard","year":"2020"},{"key":"2025101507172540500_ref005","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58565-5_6","article-title":"Podnet: pooled outputs distillation for small-tasks incremental learning","author":"Douillard","year":"2020"},{"issue":"11\/12","key":"2025101507172540500_ref006","first-page":"1","article-title":"Recent developments in computer vision and artificial intelligence aided intelligent robotic welding applications","volume":"126","author":"Eren","year":"2023","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"issue":"2","key":"2025101507172540500_ref007","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1109\/TII.2020.2977121","article-title":"Seam feature point acquisition based on efficient convolution operator and particle filter in GMAW","volume":"17","author":"Fan","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"2025101507172540500_ref008","first-page":"1","article-title":"Continual learning with structured inheritance for semantic segmentation in aerial imagery","volume":"60","author":"Feng","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"2025101507172540500_ref009","first-page":"9769","article-title":"Memory efficient experience replay for streaming learning","author":"Hayes","year":"2018"},{"issue":"7","key":"2025101507172540500_ref010","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","author":"Hinton","year":"2015","journal-title":"Computer Science"},{"issue":"13","key":"2025101507172540500_ref011","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"2025101507172540500_ref012","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1109\/THMS.2023.3251955","article-title":"A multi-sensor interface to improve the learning experience in arc welding training tasks","volume":"53","author":"Lee","year":"2023","journal-title":"IEEE Transactions on Human-Machine Systems"},{"issue":"12","key":"2025101507172540500_ref013","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025101507172540500_ref014","first-page":"2755","article-title":"Learning efficient convolutional networks through network slimming","author":"Liu","year":"2017"},{"key":"2025101507172540500_ref015","first-page":"6470","article-title":"Gradient episodic memory for continual learning","author":"Lopez-Paz","year":"2017"},{"key":"2025101507172540500_ref016","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: the sequential learning problem","volume":"24","author":"McCloskey","year":"1989","journal-title":"Psychology of Learning and Motivation"},{"key":"2025101507172540500_ref017","first-page":"1114","article-title":"Continual semantic segmentation via repulsion-attraction of sparse and disentangled latent representations","author":"Michieli","year":"2021"},{"key":"2025101507172540500_ref018","doi-asserted-by":"crossref","first-page":"103167","DOI":"10.1016\/j.cviu.2021.103167","article-title":"Knowledge distillation for incremental learning in semantic segmentation","volume":"205","author":"Michieli","year":"2021","journal-title":"Computer Vision and Image Understanding"},{"key":"2025101507172540500_ref019","first-page":"361","article-title":"Learn the new, keep the old: extending pretrained models with new anatomy and images","author":"Ozdemir","year":"2018"},{"key":"2025101507172540500_ref020","first-page":"5533","article-title":"ICARL: incremental classifier and representation learning","author":"Rebuffi","year":"2016"},{"issue":"9","key":"2025101507172540500_ref021","doi-asserted-by":"crossref","first-page":"3524","DOI":"10.1109\/JSTARS.2019.2925416","article-title":"Incremental learning for semantic segmentation of large-scale remote sensing data","volume":"12","author":"Tasar","year":"2018","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2025101507172540500_ref022","first-page":"11","volume-title":"On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities","author":"Vapnik","year":"2015"},{"issue":"8","key":"2025101507172540500_ref023","doi-asserted-by":"crossref","first-page":"5362","DOI":"10.1109\/TPAMI.2024.3367329","article-title":"A comprehensive survey of continual learning: theory, method and application","volume":"46","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025101507172540500_ref024","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmapro.2021.12.004","article-title":"Autonomous weld seam tracking under strong noise based on feature-supervised tracker-driven generative adversarial network","volume":"74","author":"Xu","year":"2022","journal-title":"Journal of Manufacturing Processes"},{"key":"2025101507172540500_ref025","doi-asserted-by":"crossref","DOI":"10.1145\/3474085.3475443","article-title":"An em framework for online incremental learning of semantic segmentation","author":"Yan","year":"2021"},{"issue":"2","key":"2025101507172540500_ref026","first-page":"1","article-title":"Uncertainty-aware contrastive distillation for incremental semantic segmentation","volume":"45","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025101507172540500_ref027","first-page":"6980","article-title":"Semantic drift compensation for class-incremental learning","author":"Yu","year":"2020"},{"key":"2025101507172540500_ref028","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume":"70","author":"Zenke","year":"2017","journal-title":"Proceedings of Machine Learning Research"},{"issue":"1","key":"2025101507172540500_ref029","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s10994-021-06056-w","article-title":"Understanding generalization error of SGD in nonconvex optimization","volume":"111","author":"Zhou","year":"2022","journal-title":"Machine Learning"},{"key":"2025101507172540500_ref030","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.optlaseng.2018.01.008","article-title":"Laser vision seam tracking system based on image processing and continuous convolution operator tracker","volume":"105","author":"Zou","year":"2018","journal-title":"Optics and Lasers in Engineering"},{"key":"2025101507172540500_ref031","doi-asserted-by":"crossref","first-page":"112492","DOI":"10.1016\/j.measurement.2023.112492","article-title":"Light-weight segmentation network based on solov2 for weld seam feature extraction","volume":"208","author":"Zou","year":"2023","journal-title":"Measurement"},{"article-title":"ENET: a deep neural network architecture for real-time semantic segmentation","year":"2016","author":"Paszke","key":"2025101507172540500_ref032"}],"container-title":["Industrial Robot: the international journal of robotics research and application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-11-2024-0528\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/ir\/article-pdf\/52\/5\/792\/10355730\/ir-11-2024-0528en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ir\/article-pdf\/52\/5\/792\/10355730\/ir-11-2024-0528en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T11:17:40Z","timestamp":1760527060000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ir\/article\/52\/5\/792\/1257339\/A-rehearsal-based-domain-incremental-learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,13]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10,16]]}},"URL":"https:\/\/doi.org\/10.1108\/ir-11-2024-0528","relation":{},"ISSN":["0143-991X","1758-5791"],"issn-type":[{"type":"print","value":"0143-991X"},{"type":"electronic","value":"1758-5791"}],"subject":[],"published":{"date-parts":[[2025,3,13]]}}}