{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T14:50:13Z","timestamp":1773240613443,"version":"3.50.1"},"reference-count":190,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.aei.2026.104515","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T21:12:18Z","timestamp":1772485938000},"page":"104515","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Human centric general physical intelligence for agile manufacturing automation"],"prefix":"10.1016","volume":"72","author":[{"given":"Sandeep","family":"Kanta","sequence":"first","affiliation":[]},{"given":"Mehrdad","family":"Tavassoli","sequence":"additional","affiliation":[]},{"given":"Varun Teja","family":"Chirkuri","sequence":"additional","affiliation":[]},{"given":"Venkata Akhil","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Santhi Bharath","family":"Punati","sequence":"additional","affiliation":[]},{"given":"Praveen","family":"Damacharla","sequence":"additional","affiliation":[]},{"given":"Sunny","family":"Katyara","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.aei.2026.104515_b1","first-page":"18","article-title":"Mass customization in practice: Strategic implementation and insights from polish small and medium sized enterprises","volume":"20","author":"Patalas-Maliszewska","year":"2025","journal-title":"Adv. Prod. Eng. Manag."},{"issue":"2","key":"10.1016\/j.aei.2026.104515_b2","doi-asserted-by":"crossref","DOI":"10.1177\/21582440251336514","article-title":"Effects of industry 4.0 on small and medium-scale enterprises: An analytical and bibliometric review","volume":"15","author":"Gold","year":"2025","journal-title":"SAGE Open"},{"key":"10.1016\/j.aei.2026.104515_b3","series-title":"Integration of Heterogeneous Manufacturing Machinery in Cells and Systems","first-page":"199","article-title":"Machine intelligence for agile manufacturing","author":"Katyara","year":"2024"},{"issue":"5","key":"10.1016\/j.aei.2026.104515_b4","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1177\/02783649241281508","article-title":"Foundation models in robotics: Applications, challenges, and the future","volume":"44","author":"Firoozi","year":"2025","journal-title":"Int. J. Robot. Res."},{"issue":"4","key":"10.1016\/j.aei.2026.104515_b5","doi-asserted-by":"crossref","first-page":"74","DOI":"10.61877\/ijmrp.v2i4.135","article-title":"Advances in autonomous robotics: integrating AI and machine learning for enhanced automation and control in industrial applications","volume":"2","author":"Singh","year":"2024","journal-title":"Int. J. Multidimens. Res. Perspect."},{"issue":"18","key":"10.1016\/j.aei.2026.104515_b6","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1080\/01691864.2024.2408593","article-title":"Real-world robot applications of foundation models: A review","volume":"38","author":"Kawaharazuka","year":"2024","journal-title":"Adv. Robot."},{"key":"10.1016\/j.aei.2026.104515_b7","article-title":"Robot learning in the era of foundation models: A survey","author":"Xiao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aei.2026.104515_b8","series-title":"Gemini robotics: Bringing ai into the physical world","author":"Team","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b9","series-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b10","series-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b11","series-title":"Conference on Robot Learning","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Zitkovich","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b12","series-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"9652","article-title":"Vision-language model-based physical reasoning for robot liquid perception","author":"Lai","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b13","series-title":"Toward general-purpose robots via foundation models: A survey and meta-analysis","author":"Hu","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b14","series-title":"Know where you\u2019re uncertain when planning with multimodal foundation models: A formal framework","author":"Bhatt","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b15","series-title":"Towards cognitive collaborative robots: Semantic-level integration and explainable control for human-centric cooperation","author":"Oh","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2024.102769","article-title":"Exploring the synergies between collaborative robotics, digital twins, augmentation, and industry 5.0 for smart manufacturing: A state-of-the-art review","volume":"89","author":"Zafar","year":"2024","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.aei.2026.104515_b17","series-title":"A survey on vision-language-action models for embodied ai","author":"Ma","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b18","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1016\/j.jmsy.2024.05.003","article-title":"A vision-language-guided robotic action planning approach for ambiguity mitigation in human\u2013robot collaborative manufacturing","volume":"74","author":"Fan","year":"2024","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.aei.2026.104515_b19","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.jmsy.2025.03.016","article-title":"H2R Bridge: Transferring vision-language models to few-shot intention meta-perception in human robot collaboration","volume":"80","author":"Wu","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"10.1016\/j.aei.2026.104515_b20","series-title":"MOSAIC: A skill-centric algorithmic framework for long-horizon manipulation planning","author":"Mishani","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b21","series-title":"Orionnav: Online planning for robot autonomy with context-aware llm and open-vocabulary semantic scene graphs","author":"Devarakonda","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b22","series-title":"Visual language maps for robot navigation","author":"Huang","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b23","series-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b24","unstructured":"T. Silver, V. Hariprasad, R.S. Shuttleworth, N. Kumar, T. Lozano-P\u00e9rez, L.P. Kaelbling, PDDL planning with pretrained large language models, in: NeurIPS 2022 Foundation Models for Decision Making Workshop, 2022."},{"issue":"2","key":"10.1016\/j.aei.2026.104515_b25","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1109\/TASE.2021.3064065","article-title":"Sim2real in robotics and automation: Applications and challenges","volume":"18","author":"H\u00f6fer","year":"2021","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104515_b26","series-title":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2651","article-title":"Learning to augment synthetic images for sim2real policy transfer","author":"Pashevich","year":"2019"},{"issue":"3","key":"10.1016\/j.aei.2026.104515_b27","doi-asserted-by":"crossref","first-page":"8399","DOI":"10.1109\/LRA.2022.3188109","article-title":"Robot learning of mobile manipulation with reachability behavior priors","volume":"7","author":"Jauhri","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"5","key":"10.1016\/j.aei.2026.104515_b28","doi-asserted-by":"crossref","first-page":"674","DOI":"10.26599\/TST.2021.9010012","article-title":"Deep reinforcement learning based mobile robot navigation: A review","volume":"26","author":"Zhu","year":"2021","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.aei.2026.104515_b29","series-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b30","series-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b31","series-title":"Ferret-v2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b32","unstructured":"E. Daxberger, N. Wenzel, D. Griffiths, H. Gang, J. Lazarow, G. Kohavi, K. Kang, M. Eichner, Y. Yang, A. Dehghan, et al., Mm-spatial: Exploring 3d spatial understanding in multimodal llms, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 7395\u20137408."},{"key":"10.1016\/j.aei.2026.104515_b33","series-title":"EmbodiedMAE: A unified 3D multi-modal representation for robot manipulation","author":"Dong","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b34","unstructured":"S. Baik, H. Kim, H. Joo, Learning 3d object spatial relationships from pre-trained 2d diffusion models, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 8418\u20138428."},{"key":"10.1016\/j.aei.2026.104515_b35","series-title":"Reasoning in space via grounding in the world","author":"Chen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b36","doi-asserted-by":"crossref","unstructured":"Z. Liu, S. Zheng, S. Chen, C. Zhao, L. Liang, X. Xue, Y. Fu, A neural representation framework with llm-driven spatial reasoning for open-vocabulary 3d visual grounding, in: Proceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 1042\u20131051.","DOI":"10.1145\/3746027.3754918"},{"key":"10.1016\/j.aei.2026.104515_b37","series-title":"European Conference on Computer Vision","first-page":"151","article-title":"Scanreason: Empowering 3d visual grounding with reasoning capabilities","author":"Zhu","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b38","series-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b39","article-title":"Causal confusion in imitation learning","volume":"32","author":"De Haan","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b40","series-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b41","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b42","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b43","series-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b44","series-title":"Rt-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b45","series-title":"International Conference on Machine Learning","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.aei.2026.104515_b46","series-title":"Pali-x: On scaling up a multilingual vision and language model","author":"Chen","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b47","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"6892","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0","author":"O\u2019Neill","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b48","series-title":"Ul2: Unifying language learning paradigms","author":"Tay","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b49","series-title":"Ok-robot: What really matters in integrating open-knowledge models for robotics","author":"Liu","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b50","series-title":"2025 IEEE International Conference on Robotics and Automation","first-page":"5930","article-title":"Robotic-clip: Fine-tuning clip on action data for robotic applications","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b51","series-title":"European Conference on Computer Vision","first-page":"728","article-title":"Simple open-vocabulary object detection","author":"Minderer","year":"2022"},{"issue":"5","key":"10.1016\/j.aei.2026.104515_b52","doi-asserted-by":"crossref","first-page":"3929","DOI":"10.1109\/TRO.2023.3281153","article-title":"Anygrasp: Robust and efficient grasp perception in spatial and temporal domains","volume":"39","author":"Fang","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.aei.2026.104515_b53","doi-asserted-by":"crossref","first-page":"55682","DOI":"10.1109\/ACCESS.2024.3387941","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"12","author":"Vemprala","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.aei.2026.104515_b54","series-title":"European Conference on Computer Vision","first-page":"140","article-title":"Palm: Predicting actions through language models","author":"Kim","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b55","series-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.aei.2026.104515_b56","series-title":"Conference on Robot Learning","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b57","series-title":"Vima: General robot manipulation with multimodal prompts","first-page":"6","author":"Jiang","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b58","series-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"10.1016\/j.aei.2026.104515_b59","first-page":"25081","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b60","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b61","series-title":"Gr00t n1: An open foundation model for generalist humanoid robots","author":"Bjorck","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b62","series-title":"Eagle 2: Building post-training data strategies from scratch for frontier vision-language models","author":"Li","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b63","series-title":"SmolLM2: When smol goes big\u2013data-centric training of a small language model","author":"Allal","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b64","series-title":"Robocat: A self-improving generalist agent for robotic manipulation","author":"Bousmalis","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b65","series-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b66","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b67","series-title":"Rt-h: Action hierarchies using language","author":"Belkhale","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b68","series-title":"\u03c00: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b69","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"23","article-title":"Domain randomization for transferring deep neural networks from simulation to the real world","author":"Tobin","year":"2017"},{"key":"10.1016\/j.aei.2026.104515_b70","series-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b71","series-title":"Gensim: Generating robotic simulation tasks via large language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b72","series-title":"RFUniverse: a multiphysics simulation platform for embodied AI","author":"Fu","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b73","series-title":"Regen: Generative robot simulation via inverse design","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b74","series-title":"A survey: Learning embodied intelligence from physical simulators and world models","author":"Long","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b75","series-title":"MuBlE: MuJoCo and blender simulation environment and benchmark for task planning in robot manipulation","author":"Nazarczuk","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b76","article-title":"Aligning cyber space with physical world: A comprehensive survey on embodied ai","author":"Liu","year":"2025","journal-title":"IEEE\/ASME Trans. Mechatronics"},{"issue":"3","key":"10.1016\/j.aei.2026.104515_b77","first-page":"719","article-title":"Cognitive digital twin-based internet of robotic things, multi-sensory extended reality and simulation modeling technologies, and generative artificial intelligence and cyber\u2013physical manufacturing systems in the immersive industrial metaverse","volume":"19","author":"Lazaroiu","year":"2024","journal-title":"Equilib. Q. J. Econ. Econ. Policy"},{"key":"10.1016\/j.aei.2026.104515_b78","series-title":"Conference on Robot Learning","first-page":"2226","article-title":"Daydreamer: World models for physical robot learning","author":"Wu","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b79","first-page":"655","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","volume":"36","author":"Majumdar","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b80","unstructured":"Q. Vuong, S. Levine, H.R. Walke, K. Pertsch, A. Singh, R. Doshi, C. Xu, J. Luo, L. Tan, D. Shah, et al., Open x-embodiment: Robotic learning datasets and rt-x models, in: Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@ CoRL2023, 2023."},{"key":"10.1016\/j.aei.2026.104515_b81","series-title":"\u03c00.5: A vision-language-action model with open-world generalization","author":"Intelligence","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b82","series-title":"TriVLA: A unified triple-system-based unified vision-language-action model for general robot control","author":"Liu","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b83","series-title":"Diffusion-VLA: Generalizable and interpretable robot foundation model via self-generated reasoning","author":"Wen","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b84","series-title":"Hamster: Hierarchical action models for open-world robot manipulation","author":"Li","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b85","series-title":"SAM-E: Leveraging visual foundation model with sequence imitation for embodied manipulation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b86","series-title":"Plan-seq-learn: Language model guided rl for solving long horizon robotics tasks","author":"Dalal","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b87","series-title":"Diffuseloco: Real-time legged locomotion control with diffusion from offline datasets","author":"Huang","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b88","series-title":"Rebot: Scaling robot learning with real-to-sim-to-real robotic video synthesis","author":"Fang","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b89","series-title":"Robotic control via embodied chain-of-thought reasoning","author":"Zawalski","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b90","unstructured":"J. Li, Y. Zhu, Z. Tang, J. Wen, M. Zhu, X. Liu, C. Li, R. Cheng, Y. Peng, Y. Peng, et al., CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025, pp. 9759\u20139769."},{"key":"10.1016\/j.aei.2026.104515_b91","series-title":"ROSA: Harnessing robot states for vision-language and action alignment","author":"Wen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b92","series-title":"Replan: Robotic replanning with perception and language models","author":"Skreta","year":"2024"},{"issue":"8","key":"10.1016\/j.aei.2026.104515_b93","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1007\/s10514-023-10131-7","article-title":"Text2motion: From natural language instructions to feasible plans","volume":"47","author":"Lin","year":"2023","journal-title":"Auton. Robots"},{"key":"10.1016\/j.aei.2026.104515_b94","series-title":"STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner","author":"Zhou","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b95","series-title":"Logic-skill programming: An optimization-based approach to sequential skill planning","author":"Xue","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b96","doi-asserted-by":"crossref","DOI":"10.1109\/TASE.2025.3567609","article-title":"Learn-gen-plan: Bridging the gap between vision language models and real-world long-horizon dexterous manipulations","author":"Hao","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104515_b97","article-title":"BOSS: Benchmark for observation space shift in long-horizon task","author":"Yang","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.aei.2026.104515_b98","article-title":"Embodied intelligence toward future smart manufacturing in the era of AI foundation model","author":"Ren","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatronics"},{"key":"10.1016\/j.aei.2026.104515_b99","series-title":"OneTwoVLA: A unified vision-language-action model with adaptive reasoning","author":"Lin","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b100","series-title":"Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b101","series-title":"Dexvla: Vision-language model with plug-in diffusion expert for general robot control","author":"Wen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b102","series-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b103","series-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b104","series-title":"Mutex: Learning unified policies from multimodal task specifications","author":"Shah","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b105","series-title":"Human-timescale adaptation in an open-ended task space","author":"Team","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b106","series-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b107","series-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"issue":"2","key":"10.1016\/j.aei.2026.104515_b108","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1002\/rob.21546","article-title":"An architecture for online affordance-based perception and whole-body planning","volume":"32","author":"Fallon","year":"2015","journal-title":"J. Field Robot."},{"key":"10.1016\/j.aei.2026.104515_b109","series-title":"Conference on Robot Learning","first-page":"1585","article-title":"Embodied semantic scene graph generation","author":"Li","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b110","series-title":"Progprompt: Generating situated robot task plans using large language models","author":"Singh","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b111","series-title":"Code as policies: Language model programs for embodied control","author":"Liang","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b112","series-title":"Code-as-symbolic-planner: Foundation model-based robot planning via symbolic code generation","author":"Chen","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b113","series-title":"Roboscript: Code generation for free-form manipulation tasks across real and simulation","author":"Chen","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b114","series-title":"OG-VLA: 3D-aware vision language action model via orthographic image generation","author":"Singh","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b115","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2025.3544909","article-title":"Tinyvla: Towards fast, data-efficient vision-language-action models for robotic manipulation","author":"Wen","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.aei.2026.104515_b116","series-title":"Hybridvla: Collaborative diffusion and autoregression in a unified vision-language-action model","author":"Liu","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b117","article-title":"Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.aei.2026.104515_b118","series-title":"Fine-tuning vision-language-action models: Optimizing speed and success","author":"Kim","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b119","series-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b120","series-title":"Ricl: Adding in-context adaptability to pre-trained vision-language-action models","author":"Sridhar","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b121","series-title":"Safety aware task planning via large language models in robotics","author":"Khan","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b122","series-title":"Robots that ask for help: Uncertainty alignment for large language model planners","author":"Ren","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b123","series-title":"Conference on Robot Learning","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","author":"Ha","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b124","series-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b125","series-title":"Generating robot constitutions & benchmarks for semantic safety","author":"Sermanet","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b126","first-page":"31967","article-title":"Large language models as commonsense knowledge for large-scale task planning","volume":"36","author":"Zhao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b127","series-title":"Rap: Retrieval-augmented planning with contextual memory for multimodal llm agents","author":"Kagaya","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b128","series-title":"Mastering robot manipulation with multimodal prompts through pretraining and multi-task fine-tuning","author":"Li","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b129","unstructured":"A. Muppidi, Synthetic Manipulation Data Generation using Large Language Models to Train Real-World Language-Conditioned Robotic Manipulation Agents."},{"issue":"2","key":"10.1016\/j.aei.2026.104515_b130","doi-asserted-by":"crossref","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","article-title":"Rlbench: The robot learning benchmark & learning environment","volume":"5","author":"James","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.aei.2026.104515_b131","series-title":"A two-stage fine-tuning strategy for generalizable manipulation skill of embodied AI","author":"Gao","year":"2023"},{"issue":"3","key":"10.1016\/j.aei.2026.104515_b132","doi-asserted-by":"crossref","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","article-title":"Calvin: A benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks","volume":"7","author":"Mees","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.aei.2026.104515_b133","series-title":"Conference on Robot Learning","first-page":"1723","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Walke","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b134","series-title":"Maniskill2: A unified benchmark for generalizable manipulation skills","author":"Gu","year":"2023"},{"issue":"11","key":"10.1016\/j.aei.2026.104515_b135","first-page":"28","article-title":"Key performance indicators and supply chain efficiencies associated with implementing collaborative robotic arms in large-scale food processing plants","volume":"9","author":"Hakimi","year":"2024","journal-title":"Open J. Robot. Auton. Decision-Mak. Human-Mach. Interact."},{"issue":"9","key":"10.1016\/j.aei.2026.104515_b136","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1038\/s42254-022-00481-z","article-title":"A concise guide to modelling the physics of embodied intelligence in soft robotics","volume":"4","author":"Mengaldo","year":"2022","journal-title":"Nat. Rev. Phys."},{"key":"10.1016\/j.aei.2026.104515_b137","series-title":"CoinRobot: Generalized end-to-end robotic learning for physical intelligence","author":"Zhao","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b138","series-title":"The Mathematics and Engineering of NVIDIA\u2019s Cosmos Models for Physical AI (January 08, 2025)","article-title":"The mathematics and engineering of NVIDIA\u2019s cosmos models for physical AI","author":"Alonso","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b139","series-title":"European Robotics Forum","first-page":"216","article-title":"Reflective understanding for dependable robots","author":"Sanz","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b140","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2022.102360","article-title":"Robot learning towards smart robotic manufacturing: A review","volume":"77","author":"Liu","year":"2022","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"10.1016\/j.aei.2026.104515_b141","series-title":"2022 International Conference on Robotics and Automation","first-page":"10781","article-title":"Gelslim 3.0: High-resolution measurement of shape, force and slip in a compact tactile-sensing finger","author":"Taylor","year":"2022"},{"key":"10.1016\/j.aei.2026.104515_b142","series-title":"2025 IEEE International Conference on Robotics and Automation","first-page":"8249","article-title":"Rt-affordance: Affordances are versatile intermediate representations for robot manipulation","author":"Nasiriany","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b143","article-title":"Exploring embodied multimodal large models: Development, datasets, and future directions","author":"Chen","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.aei.2026.104515_b144","first-page":"124420","article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.aei.2026.104515_b145","series-title":"Benchmarking vision, language, & action models on robotic learning tasks","author":"Guruprasad","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b146","article-title":"AffordStruct: Weakly supervised affordance grounding based on spatial interaction and knowledge-aware","author":"Wang","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104515_b147","doi-asserted-by":"crossref","unstructured":"J. Lu, C. Clark, S. Lee, Z. Zhang, S. Khosla, R. Marten, D. Hoiem, A. Kembhavi, Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26439\u201326455.","DOI":"10.1109\/CVPR52733.2024.02497"},{"issue":"7960","key":"10.1016\/j.aei.2026.104515_b148","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1038\/s41586-023-06031-6","article-title":"Learnable latent embeddings for joint behavioural and neural analysis","volume":"617","author":"Schneider","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.aei.2026.104515_b149","series-title":"2024 21st International Conference on Ubiquitous Robots","first-page":"490","article-title":"M2CURL: sample-efficient multimodal reinforcement learning via self-supervised representation learning for robotic manipulation","author":"Lygerakis","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b150","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129376","article-title":"MMTF-DES: A fusion of multimodal transformer models for desire, emotion, and sentiment analysis of social media data","volume":"623","author":"Aziz","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.aei.2026.104515_b151","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102147","article-title":"CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach","volume":"103","author":"Li","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.aei.2026.104515_b152","doi-asserted-by":"crossref","unstructured":"E. Schonfeld, S. Ebrahimi, S. Sinha, T. Darrell, Z. Akata, Generalized zero-and few-shot learning via aligned variational autoencoders, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 8247\u20138255.","DOI":"10.1109\/CVPR.2019.00844"},{"key":"10.1016\/j.aei.2026.104515_b153","article-title":"HGTFM: Hierarchical gating-driven transformer fusion model for robust multimodal sentiment analysis","author":"Yang","year":"2025","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.aei.2026.104515_b154","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/TRO.2019.2959445","article-title":"Making sense of vision and touch: Learning multimodal representations for contact-rich tasks","volume":"36","author":"Lee","year":"2020","journal-title":"IEEE Trans. Robot."},{"issue":"11","key":"10.1016\/j.aei.2026.104515_b155","doi-asserted-by":"crossref","first-page":"2163","DOI":"10.3390\/electronics14112163","article-title":"Haptic\u2013Vision fusion for accurate position identification in robotic multiple peg-in-hole assembly","volume":"14","author":"Chen","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.aei.2026.104515_b156","series-title":"Forcevla: Enhancing VLA models with a force-aware MoE for contact-rich manipulation","author":"Yu","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b157","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2023.1280773","article-title":"Vision-force-fused curriculum learning for robotic contact-rich assembly tasks","volume":"17","author":"Jin","year":"2023","journal-title":"Front. Neurorobotics"},{"issue":"1","key":"10.1016\/j.aei.2026.104515_b158","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TRO.2007.914848","article-title":"Learning object affordances: from sensory\u2013motor coordination to imitation","volume":"24","author":"Montesano","year":"2008","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.aei.2026.104515_b159","series-title":"Benchmarking Sim2Real gap: High-fidelity digital twinning of agile manufacturing","author":"Katyara","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b160","series-title":"Data-link: High fidelity manufacturing datasets for Model2Real transfer under industrial settings","author":"Katyara","year":"2023"},{"issue":"3","key":"10.1016\/j.aei.2026.104515_b161","doi-asserted-by":"crossref","first-page":"3205","DOI":"10.1109\/TASE.2023.3276856","article-title":"Vision-and tactile-based continuous multimodal intention and attention recognition for safer physical human\u2013robot interaction","volume":"21","author":"Wong","year":"2023","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"10.1016\/j.aei.2026.104515_b162","series-title":"AToM-Bot: Embodied fulfillment of unspoken human needs with affective theory of mind","author":"Ding","year":"2024"},{"issue":"4","key":"10.1016\/j.aei.2026.104515_b163","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1109\/TCDS.2021.3110406","article-title":"Leveraging kernelized synergies on shared subspace for precision grasping and dexterous manipulation","volume":"15","author":"Katyara","year":"2021","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.aei.2026.104515_b164","article-title":"Advancing multi-modal beam prediction with cross-modal feature enhancement and dynamic fusion mechanism","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.aei.2026.104515_b165","series-title":"Grasping materialities: Making sense through explorative touch interactions with materials and digital technologies","author":"S\u00f8yland","year":"2021"},{"key":"10.1016\/j.aei.2026.104515_b166","series-title":"Perception, reason, think, and plan: A survey on large multimodal reasoning models","author":"Li","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b167","series-title":"Large language models for manufacturing","author":"Li","year":"2024"},{"issue":"5","key":"10.1016\/j.aei.2026.104515_b168","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.1109\/TCYB.2023.3310505","article-title":"Multimodality driven impedance-based sim2real transfer learning for robotic multiple peg-in-hole assembly","volume":"54","author":"Chen","year":"2023","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.aei.2026.104515_b169","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103258","article-title":"Handling new target classes in semantic segmentation with domain adaptation","volume":"212","author":"Bucher","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.aei.2026.104515_b170","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"2086","article-title":"Task and motion planning with large language models for object rearrangement","author":"Ding","year":"2023"},{"issue":"1","key":"10.1016\/j.aei.2026.104515_b171","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/TCDS.2023.3296166","article-title":"Learning skills from demonstrations: A trend from motion primitives to experience abstraction","volume":"16","author":"Tavassoli","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"10.1016\/j.aei.2026.104515_b172","series-title":"Model compression via distillation and quantization","author":"Polino","year":"2018"},{"key":"10.1016\/j.aei.2026.104515_b173","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101945","article-title":"Computational approaches to explainable artificial intelligence: advances in theory, applications and trends","volume":"100","author":"G\u00f3rriz","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.aei.2026.104515_b174","series-title":"Physics-driven data generation for contact-rich manipulation via trajectory optimization","author":"Yang","year":"2025"},{"key":"10.1016\/j.aei.2026.104515_b175","series-title":"Deep generative models in robotics: A survey on learning from multimodal demonstrations","author":"Urain","year":"2024"},{"key":"10.1016\/j.aei.2026.104515_b176","series-title":"2025 IEEE International Conference on Robotics and Automation","first-page":"4853","article-title":"Spot: Se (3) pose trajectory diffusion for object-centric manipulation","author":"Hsu","year":"2025"},{"issue":"11","key":"10.1016\/j.aei.2026.104515_b177","doi-asserted-by":"crossref","first-page":"7327","DOI":"10.1109\/TPAMI.2021.3116668","article-title":"Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models","volume":"44","author":"Bond-Taylor","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.aei.2026.104515_b178","series-title":"Towards generalist robots: A promising paradigm via generative simulation","author":"Xian","year":"2023"},{"key":"10.1016\/j.aei.2026.104515_b179","article-title":"M 2 diffuser: Diffusion-based trajectory optimization for mobile manipulation in 3d scenes","author":"Yan","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.aei.2026.104515_b180","series-title":"Aligning diffusion model with problem constraints for trajectory optimization","author":"Li","year":"2025"},{"issue":"12","key":"10.1016\/j.aei.2026.104515_b181","doi-asserted-by":"crossref","first-page":"3903","DOI":"10.1080\/00207543.2018.1471243","article-title":"Digital twin-driven rapid individualised designing of automated flow-shop manufacturing system","volume":"57","author":"Liu","year":"2019","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.aei.2026.104515_b182","first-page":"1","article-title":"Digital twin designs with generative AI: crafting a comprehensive framework for manufacturing systems","author":"Mata","year":"2025","journal-title":"J. Intell. Manuf."},{"key":"10.1016\/j.aei.2026.104515_b183","series-title":"2025 IEEE International Conference on Robotics and Automation","first-page":"8203","article-title":"COLLAGE: Collaborative human-agent interaction generation using hierarchical latent diffusion and language models","author":"Daiya","year":"2025"},{"issue":"6","key":"10.1016\/j.aei.2026.104515_b184","doi-asserted-by":"crossref","first-page":"3166","DOI":"10.3390\/app15063166","article-title":"Generative AI in AI-based digital twins for fault diagnosis for predictive maintenance in Industry 4.0\/5.0","volume":"15","author":"Miko\u0142ajewska","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.aei.2026.104515_b185","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2023.1241522","article-title":"The MAS4AI framework for human-centered agile and smart manufacturing","volume":"6","author":"Sidorenko","year":"2023","journal-title":"Front. Artif. Intell."},{"issue":"5","key":"10.1016\/j.aei.2026.104515_b186","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1080\/00207543.2023.2200567","article-title":"Dynamic distributed decision-making for resilient resource reallocation in disrupted manufacturing systems","volume":"62","author":"Bi","year":"2024","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.aei.2026.104515_b187","series-title":"Proceedings Autonomous Decentralized Systems","first-page":"167","article-title":"Decentralized architecture for fault tolerant multi agent system","author":"Khan","year":"2005"},{"issue":"13","key":"10.1016\/j.aei.2026.104515_b188","doi-asserted-by":"crossref","first-page":"4302","DOI":"10.1080\/00207543.2022.2089929","article-title":"Blockchained smart contract pyramid-driven multi-agent autonomous process control for resilient individualised manufacturing towards Industry 5.0","volume":"61","author":"Leng","year":"2023","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.aei.2026.104515_b189","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.jmsy.2021.02.010","article-title":"Digital twin-driven online anomaly detection for an automation system based on edge intelligence","volume":"59","author":"Huang","year":"2021","journal-title":"J. Manuf. Syst."},{"issue":"2","key":"10.1016\/j.aei.2026.104515_b190","doi-asserted-by":"crossref","first-page":"898","DOI":"10.3390\/app14020898","article-title":"Artificial intelligence for predictive maintenance applications: key components, trustworthiness, and future trends","volume":"14","author":"Ucar","year":"2024","journal-title":"Appl. Sci."}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626002077?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1474034626002077?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:13:53Z","timestamp":1773170033000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1474034626002077"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":190,"alternative-id":["S1474034626002077"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104515","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Human centric general physical intelligence for agile manufacturing automation","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104515","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104515"}}