{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T07:47:55Z","timestamp":1782028075055,"version":"3.54.5"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Eindhoven Artificial Intelligence Systems Institute"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Engineering with Computers"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Conventional toolpath strategies in additive manufacturing often ignore the underlying physics, leading to defects and inefficiency. In this paper, we present a reinforcement learning framework that couples policy learning directly with finite-element thermal simulations for powder bed fusion, enabling agents to learn adaptive toolpaths from spatially resolved temperature feedback. Using procedurally generated geometries to ensure robust generalization, we train Deep Q-Network and Proximal Policy Optimization agents in both simplified and thermally coupled environments. Our results demonstrate that learned policies outperform conventional zigzag baselines in terms of speed and generalize effectively to irregular geometries, discovering emergent thermal strategies such as outside-to-inside scanning patterns.<\/jats:p>","DOI":"10.1007\/s00366-026-02334-0","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T09:19:13Z","timestamp":1778059153000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning-based toolpath planning for bed-based additive manufacturing"],"prefix":"10.1007","volume":"42","author":[{"given":"R.","family":"Schmeitz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. J. M.","family":"Wolfs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. J. C.","family":"Remmers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2334_CR1","doi-asserted-by":"publisher","first-page":"2950","DOI":"10.1016\/j.jmrt.2022.02.054","volume":"17","author":"S-G Chen","year":"2022","unstructured":"Chen S-G, Gao H-J, Zhang Y-D, Wu Q, Gao Z-H, Zhou X (2022) Review on residual stresses in metal additive manufacturing: formation mechanisms, parameter dependencies, prediction and control approaches. J Market Res 17:2950\u20132974. https:\/\/doi.org\/10.1016\/j.jmrt.2022.02.054","journal-title":"J Market Res"},{"issue":"2","key":"2334_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cossms.2021.100974","volume":"26","author":"A Mostafaei","year":"2022","unstructured":"Mostafaei A, Zhao C, He Y, Ghiaasiaan SR, Shi B, Shao S, Shamsaei N, Wu Z, Khouraytem N, Sun T, Pauza J, Gordon JV, Webler B, Parab ND, Asherloo M, Guo Q, Chen L, Rollett AD (2022) Defects and anomalies in powder bed fusion metal additive manufacturing. Curr Opin Solid State Mater Sci 26(2):100974. https:\/\/doi.org\/10.1016\/j.cossms.2021.100974","journal-title":"Curr Opin Solid State Mater Sci"},{"key":"2334_CR3","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.jmapro.2021.12.064","volume":"75","author":"N Ahmed","year":"2022","unstructured":"Ahmed N, Barsoum I, Haidemenopoulos GZ, Abu Al-Rub RK (2022) Process parameter selection and optimization of laser powder bed fusion for 316l stainless steel: a review. J Manuf Process 75:415\u2013434. https:\/\/doi.org\/10.1016\/j.jmapro.2021.12.064","journal-title":"J Manuf Process"},{"key":"2334_CR4","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.jmapro.2021.03.054","volume":"65","author":"I Drstven\u0161ek","year":"2021","unstructured":"Drstven\u0161ek I, Zupani\u010d F, Bon\u010dina T, Pal S (2021) Influence of local heat flow variations on geometrical deflections, microstructure, and tensile properties of ti-6al-4v products in powder bed fusion systems. J Manuf Process 65:382\u2013396. https:\/\/doi.org\/10.1016\/j.jmapro.2021.03.054","journal-title":"J Manuf Process"},{"issue":"3","key":"2334_CR5","doi-asserted-by":"publisher","first-page":"482","DOI":"10.3390\/met12030482","volume":"12","author":"J Munk","year":"2022","unstructured":"Munk J, Breitbarth E, Siemer T, Pirch N, H\u00e4fner C (2022) Geometry effect on microstructure and mechanical properties in laser powder bed fusion of ti-6al-4v. Metals 12(3):482. https:\/\/doi.org\/10.3390\/met12030482","journal-title":"Metals"},{"issue":"10","key":"2334_CR6","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.3390\/ma11101821","volume":"11","author":"D Wang","year":"2018","unstructured":"Wang D, Yang Y, Yi Z, Zhang M, Hao L, Bai Y, Yang Y (2018) The effect of a scanning strategy on the residual stress of 316l steel parts fabricated by selective laser melting (slm). Materials 11(10):1821. https:\/\/doi.org\/10.3390\/ma11101821","journal-title":"Materials"},{"issue":"01","key":"2334_CR7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.4236\/msa.2018.91002","volume":"09","author":"MS Alsoufi","year":"2018","unstructured":"Alsoufi MS, Elsayed AE (2018) Surface roughness quality and dimensional accuracy\u2013a comprehensive analysis of 100% infill printed parts fabricated by a personal\/desktop cost-effective FDM 3D printer. Mater Sci Appl 09(01):11\u201340. https:\/\/doi.org\/10.4236\/msa.2018.91002","journal-title":"Mater Sci Appl"},{"key":"2334_CR8","doi-asserted-by":"publisher","DOI":"10.1115\/1.4067325","author":"M Khrenov","year":"2025","unstructured":"Khrenov M, Templeton WF, Narra SP (2025) ADDOPT: An additive manufacturing optimal control framework demonstrated in minimizing layer-level thermal variance in electron beam powder bed fusion. J Manuf Sci Eng. https:\/\/doi.org\/10.1115\/1.4067325","journal-title":"J Manuf Sci Eng"},{"issue":"4","key":"2334_CR9","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1007\/s00466-021-02079-1","volume":"67","author":"DH Kim","year":"2021","unstructured":"Kim DH, Zohdi TI (2021) Tool path optimization of selective laser sintering processes using deep learning. Comput Mech 67(4):772\u2013789. https:\/\/doi.org\/10.1007\/s00466-021-02079-1","journal-title":"Comput Mech"},{"issue":"7","key":"2334_CR10","doi-asserted-by":"publisher","first-page":"633","DOI":"10.3390\/mi11070633","volume":"11","author":"J Jiang","year":"2020","unstructured":"Jiang J, Ma Y (2020) Path planning strategies to optimize accuracy, quality, build time and material use in additive manufacturing: a review. Micromachines 11(7):633. https:\/\/doi.org\/10.3390\/mi11070633","journal-title":"Micromachines"},{"key":"2334_CR11","doi-asserted-by":"publisher","unstructured":"Hong G, Yang Z, Lu Y, Lane B, Yeung H, Kim J (2024) Multi-scale model predictive control for laser powder bed fusion additive manufacturing. In: Proceedings of the ASME 2024 international design engineering technical conferences and computers and information in engineering conference (IDETC\/CIE 2024). ASME, Washington, DC, USA. https:\/\/doi.org\/10.1115\/DETC2024-143601","DOI":"10.1115\/DETC2024-143601"},{"key":"2334_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2021.102033","volume":"46","author":"F Ogoke","year":"2021","unstructured":"Ogoke F, Farimani AB (2021) Thermal control of laser powder bed fusion using deep reinforcement learning. Addit Manuf 46:102033. https:\/\/doi.org\/10.1016\/j.addma.2021.102033","journal-title":"Addit Manuf"},{"key":"2334_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2023.103937","volume":"79","author":"M Qin","year":"2024","unstructured":"Qin M, Ding J, Qu S, Song X, Wang CCL, Liao WH (2024) Deep reinforcement learning based toolpath generation for thermal uniformity in laser powder bed fusion process. Addit Manuf 79:103937. https:\/\/doi.org\/10.1016\/j.addma.2023.103937","journal-title":"Addit Manuf"},{"key":"2334_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2023.103556","volume":"71","author":"S Dharmadhikari","year":"2023","unstructured":"Dharmadhikari S, Menon N, Basak A (2023) A reinforcement learning approach for process parameter optimization in additive manufacturing. Addit Manuf 71:103556. https:\/\/doi.org\/10.1016\/j.addma.2023.103556","journal-title":"Addit Manuf"},{"key":"2334_CR15","unstructured":"Mozaffar M, Ebrahimi A, Cao J (2020) Toolpath design for additive manufacturing using deep reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.2009.14365. arXiv:2009.14365"},{"key":"2334_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.addma.2025.104912","volume":"110","author":"X Li","year":"2025","unstructured":"Li X, Pattinson SW (2025) An efficient and uncertainty-aware reinforcement learning framework for quality assurance in extrusion additive manufacturing. Addit Manuf 110:104912. https:\/\/doi.org\/10.1016\/j.addma.2025.104912","journal-title":"Addit Manuf"},{"key":"2334_CR17","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1016\/j.jmsy.2022.11.008","volume":"65","author":"J Chung","year":"2022","unstructured":"Chung J, Shen B, Law ACC, Kong ZJ (2022) Reinforcement learning-based defect mitigation for quality assurance of additive manufacturing. J Manuf Syst 65:822\u2013835. https:\/\/doi.org\/10.1016\/j.jmsy.2022.11.008","journal-title":"J Manuf Syst"},{"key":"2334_CR18","doi-asserted-by":"publisher","unstructured":"Watanabe S (2023) Tree-structured Parzen estimator: understanding its algorithm components and their roles for better empirical performance. https:\/\/doi.org\/10.48550\/arXiv.2304.11127","DOI":"10.48550\/arXiv.2304.11127"},{"key":"2334_CR19","unstructured":"Cobbe K, Hesse C, Hilton J, Schulman J (2020) Leveraging procedural generation to benchmark reinforcement learning. In: Proceedings of the 37th international conference on machine learning (ICML). Proceedings of machine learning research, vol. 119, pp. 2048\u20132056. https:\/\/doi.org\/10.48550\/arXiv.1912.01588. arXiv:1912.01588"},{"issue":"7540","key":"2334_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"2334_CR21","doi-asserted-by":"publisher","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"2334_CR22","unstructured":"OpenAI (2025) ChatGPT. https:\/\/chatgpt.com\/. Accessed 14 Jan 2026"}],"container-title":["Engineering with Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-026-02334-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00366-026-02334-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00366-026-02334-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T07:06:28Z","timestamp":1782025588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00366-026-02334-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":22,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2334"],"URL":"https:\/\/doi.org\/10.1007\/s00366-026-02334-0","relation":{},"ISSN":["0177-0667","1435-5663"],"issn-type":[{"value":"0177-0667","type":"print"},{"value":"1435-5663","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"14 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"101"}}