Rapid iterative design of reconfigurable smart products via Human–AI collaboration and digital twin feedback
DOI:
https://doi.org/10.4108/eetsis.14186Keywords:
reconfigurable smart products, CAD refinement, human–AI collaboration, constraint feedback, digital twin validationAbstract
INTRODUCTION: Parametric CAD models for reconfigurable smart products require repeated modification and virtual verification. Existing CAD generation, human–AI co-design, and simulation-assisted validation methods often separate feedback analysis, constraint checking, and CAD editing, limiting the direct use of feedback for executable refinement.
OBJECTIVES: This study develops a closed-loop CAD refinement framework that converts design feedback and digital twin–based simulation or constraint feedback into coordinated edit actions while reducing constraint violations, ineffective revisions, and oscillatory updates.
METHODS: A conflict-aware dual-feedback framework is proposed. Design feedback is translated into target parameters, local regions, modification directions, and command-level edit conditions. Simulation and constraint results are written back as violation-aware correction cues. When feedback sources conflict, active constraints, historical modification states, and edit magnitudes are jointly considered to generate controlled parameter and operation-sequence updates. The framework is evaluated on feedback-driven benchmarks constructed from the public DeepCAD and SketchGraphs datasets.
RESULTS: On the constructed DeepCAD benchmark, the proposed method achieved a constraint satisfaction rate of 90.6% and an average iteration count of 3.43. On the constructed SketchGraphs benchmark, it obtained 89.4% and 3.61, respectively. It outperformed the strongest comparison methods in constraint satisfaction and iterative efficiency while maintaining competitive CAD validity and edit-action accuracy. Statistical and ablation analyses confirmed the contributions of feedback translation, correction write-back, and conflict-aware coordination.
CONCLUSION: The results demonstrate the effectiveness of the proposed closed-loop refinement framework under the constructed feedback-driven benchmark settings, particularly in improving constraint satisfaction, reducing refinement rounds, and maintaining stable optimization under conflicting feedback.
References
[1] Khan, M. S., Sinha, S., Sheikh, T. U., Stricker, D., Ali, S. A., & Afzal, M. Z. (2024). Text2cad: Generating sequential cad designs from beginner-to-expert level text prompts. Advances in Neural Information Processing Systems, 37, 7552-7579.
[2] Li, X., Song, Y., Lou, Y., & Zhou, X. (2024, October). Cad translator: An effective drive for text to 3d parametric computer-aided design generative modeling. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 8461-8470).
[3] Liu, Y., Obukhov, A., Wegner, J. D., & Schindler, K. (2024). Point2cad: Reverse engineering cad models from 3d point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3763-3772).
[4] Ma, W., Chen, S., Lou, Y., Li, X., & Zhou, X. (2024). Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 27154-27163).
[5] Stauss, T., Wolniak, P., Tergeist, M., Wurst, J., & Lachmayer, R. (2025). Enhancing product design with digital twins: framework and application in an industry case study. Proceedings of the Design Society, 5, 1555-1564.
[6] Wang, P., Khinvasara, Y., Creijghton, G. J., Scholing, T., Wang, Y., Zhou, Z., Childs, P. R. N., & Yin, Y. (2025). Enhancing designer creativity through human–AI co-ideation: A co-creation framework for design ideation with custom GPT. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, 39, e22.
[7] Li, X., Lou, Y., Song, Y., & Zhou, X. (2025, April). Mamba-cad: State space model for 3d computer-aided design generative modeling. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 5, pp. 5013-5021).
[8] Alrashedy, K., Tambwekar, P., Zaidi, Z. H., Langwasser, M., Xu, W., & Gombolay, M. (2025, May). Generating cad code with vision-language models for 3d designs. In International Conference on Learning Representations (Vol. 2025, pp. 52236-52262).
[9] Li, J., Ma, W., Li, X., Lou, Y., Zhou, G., & Zhou, X. (2025). CAD-Llama: leveraging large language models for computer-aided design parametric 3D model generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18563-18573).
[10] Liao, J., Xu, J., Sun, Y., Tang, M., He, S., Liao, J., Yu, S., Li, Y., & Guan, X. (2025). Automated CAD modeling sequence generation from text descriptions via transformer-based large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 21720–21748)..
[11] Xu, X., Lambourne, J., Jayaraman, P., Wang, Z., Willis, K., & Furukawa, Y. (2024). Brepgen: A b-rep generative diffusion model with structured latent geometry. ACM Transactions on Graphics (TOG), 43(4), 1-14.
[12] Zhang, Z., Sun, S., Wang, W., Cai, D., & Bian, J. (2025, May). Flexcad: Unified and versatile controllable cad generation with fine-tuned large language models. In International Conference on Learning Representations (Vol. 2025, pp. 3204-3227).
[13] Deng, L., Bai, Y., Dai, Y., Huang, X., Gan, H., Huang, D., Jiacheng, H., & Shi, Y. (2025). MamTiff-CAD: Multi-scale latent diffusion with Mamba+ for complex parametric sequence. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10517–10526).
[14] Li, P., Zhang, W., Guo, J., Chen, J., & Yan, D. M. (2025, April). Revisiting cad model generation by learning raster sketch. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 5, pp. 4869-4877).
[15] Li, Y., Lin, C., Liu, Y., Long, X., Zhang, C., Wang, N., Li, X., Wang, W., & Guo, X. (2025). CADDreamer: CAD object generation from single-view images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 21448–21457).
[16] Mallis, D., Karadeniz, A. S., Cavada, S., Rukhovich, D., Foteinopoulou, N., Cherenkova, K., Kacem, A., & Aouada, D. (2025). CAD-Assistant: Tool-augmented VLLMs as generic CAD task solvers. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 7284–7294).
[17] Lee, M., Zhang, D., Jambon, C., & Kim, Y. M. (2025, August). Brepdiff: Single-stage b-rep diffusion model. In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers (pp. 1-11).
[18] Liu, Y., Xu, D., Yu, X., Xu, X., Cohen-Or, D., Zhang, H., & Huang, H. (2025). HoLa: B-Rep generation using a holistic latent representation. ACM Transactions on Graphics, 44(4), 1–25.
[19] Casey, E., Zhang, T., Ishida, S., Thompson, J. R., Khasahmadi, A., Lambourne, J. G., Jayaraman, P. K., & Willis, K. D. D. (2025). Aligning constraint generation with design intent in parametric CAD. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 8613–8622).
[20] Zhou, J., Camba, J. D., & Company, P. (2026). CADialogue: A multimodal LLM-powered conversational assistant for intuitive parametric CAD modeling. Computer-Aided Design, 191, 104006.
[21] Wang, W. F., Lu, C. T., Ponsa i Campanyà, N., Chen, B. Y., & Chen, M. Y. (2025, April). AIdeation: Designing a human-AI collaborative ideation system for concept designers. In Proceedings of the 2025 chi conference on human factors in computing systems (pp. 1-28).
[22] Yao, J., Chen, P., Li, Z., Cai, Y., Wu, Y., You, W., & Sun, L. (2025). StepIdeator: Utilizing mixed representations to support step-by-step design with generative artificial intelligence. Journal of Mechanical Design, 147(7), 071703.
[23] Edwards, K. M., Man, B., & Ahmed, F. (2024). Sketch2Prototype: rapid conceptual design exploration and prototyping with generative AI. Proceedings of the Design Society, 4, 1989-1998.
[24] Koyama, Y., & Goto, M. (2022, October). BO as assistant: Using Bayesian optimization for asynchronously generating design suggestions. In Proceedings of the 35th annual ACM symposium on user interface software and technology (pp. 1-14).
[25] Nandy, A., & Goucher-Lambert, K. (2026). Exploring the effectiveness of interactive preference learning for adapting designs to abstract semantic attributes. Journal of Mechanical Design, 148(4), 041702.
[26] Anwer, N., Stark, R., Tao, F., & Erkoyuncu, J. A. (2025). Developing and leveraging digital twins in engineering design. CIRP Annals, 74(2), 843-868.
[27] Zhang, Y., Bertoni, M., Bertoni, A., Larsson, A., & Larsson, T. (2025). Leveraging digital twins for value-driven design in smart product-service systems: the super-system digital twin framework and SEV case study. Design Science, 11, e24.
[28] Mercat, F., Le Masson, P., & Weil, B. (2025). The unique feature of designing with digital twin uncovered by design theory. Proceedings of the Design Society, 5, 3101-3110.
[29] Machacek, Z., Hercik, R., Vaclavik, A., Zemanek, J., Hameed, I. A., & Koziorek, J. (2025). Modern trends and industrial use cases of digital twin technology with 3D behavioral representation. Journal of Intelligent Manufacturing, 1-34.
[30] Mata, O., Ponce, P., Perez, C., Ramirez, M., Anthony, B., Russel, B., Apte, P., MacCleery, B., & Molina, A. (2026). Digital twin designs with generative AI: Crafting a comprehensive framework for manufacturing systems. Journal of Intelligent Manufacturing. 37, 1049–1072.
[31] Sun, Z., Wang, Y., Guo, W., & Meng, Q. (2026). Human-in-the-Loop Digital Twin Modeling for Smart Civil Infrastructure Operation and Maintenance. Applied Sciences, 16(4), 1848.
[32] Ruzarovsky, R., Horak, T., Zelník, R., Skypala, R., Csekei, M., Šido, J., Nemlaha, E., & Kopcek, M. (2025). Development and validation of digital twin behavioural model for virtual commissioning of cyber-physical system. Applied Sciences, 15(5), 2859.
[33] Papacharalampopoulos, A., Sabatakakis, K., Karagianni, O. M., & Stavropoulos, P. (2024, October). Digital Twins of Manufacturing Processes Under Industry 5.0. In European Symposium on Artificial Intelligence in Manufacturing (pp. 3-11). Cham: Springer Nature Switzerland.
[34] Willis, K. D. D., Pu, Y., Luo, J., Chu, H., Du, T., Lambourne, J. G., Solar-Lezama, A., & Matusik, W. (2021). Fusion 360 Gallery: A dataset and environment for programmatic CAD construction from human design sequences. ACM Transactions on Graphics, 40(4), Article 54.
[35] Li, C., Pan, H., Bousseau, A., & Mitra, N. J. (2020). Sketch2cad: Sequential cad modeling by sketching in context. ACM Transactions on Graphics (TOG), 39(6), 1-14.
[36] Li, C., Pan, H., Bousseau, A., & Mitra, N. J. (2022). Free2cad: Parsing freehand drawings into cad commands. ACM Transactions on Graphics (TOG), 41(4), 1-16.
[37] Para W, Bhat S, Guerrero P, Kelly T, Mitra N, Guibas LJ, et al. (2021). Sketchgen: Generating constrained cad sketches. Advances in Neural Information Processing Systems, 34, 5077-5088.
[38] Dupont, E., Cherenkova, K., Mallis, D., Gusev, G., Kacem, A., & Aouada, D. (2024, September). Transcad: A hierarchical transformer for cad sequence inference from point clouds. In European Conference on Computer Vision (pp. 19-36). Cham: Springer Nature Switzerland.
[39] Wang, X., Zheng, J., Hu, Y., Zhu, H., Yu, Q., & Zhou, Z. (2025, April). From 2d cad drawings to 3d parametric models: A vision-language approach. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 8, pp. 7961-7969).
[40] Qin, F., Lu, S., Hou, J., Wang, C., Fang, M., & Liu, L. (2025, October). Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 10573-10582).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zhifang Shi, Xue Bai, Jiahui Zhou
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
