AIGC赋能汽车设计的技术逻辑与未来趋势

许迅, 李亚军, 赵思行

包装工程(设计栏目) ›› 2025, Vol. 46 ›› Issue (22) : 319-330.

PDF(2017 KB)
PDF(2017 KB)
包装工程(设计栏目) ›› 2025, Vol. 46 ›› Issue (22) : 319-330. DOI: 10.19554/j.cnki.1001-3563.2025.22.029
设计研讨

AIGC赋能汽车设计的技术逻辑与未来趋势

  • 许迅1,2, 李亚军1,*, 赵思行3
作者信息 +

Technological Logic and Future Trends of AIGC Empowering Automotive Design

  • XU Xun1,2, LI Yajun1,*, ZHAO Sixing3
Author information +
文章历史 +

摘要

目的 探讨生成式人工智能(AIGC)发展历史,以及其在汽车设计中的技术逻辑、应用方法、现存问题与发展趋势。方法 通过梳理近年来国内外相关文献及应用案例,分析其在汽车设计中的技术平台、应用步骤及主要技术类别,探讨AIGC赋能汽车设计的具体应用场景。主要包括外观设计与风格延续、座舱设计与体验优化、HMI设计与可信交互、数字孪生与无人驾驶领域4个方面。最后,结合自动驾驶、人机共驾的产业需求,探讨AIGC在汽车设计中的挑战与趋势。结论 AIGC在汽车设计中展现出极大的潜力,能够提升设计效率、增强用户体验,特别是在HMI设计中促进人机交互信任的构建和人机共驾的实现。未来,AIGC将推动智能化设计的突破,助力智能驾驶的进一步发展。

Abstract

The work aims to explore the historical development of Artificial Intelligence Generated Content (AIGC), and its technological logic, application methods, existing issues, and future trends in automotive design. Recent literature and application cases from both domestic and international contexts were reviewed to analyze the technological platforms, application steps, and main technical categories of AIGC in automotive design. Specific application scenarios empowered by AIGC were investigated, with a focus on four key areas: exterior design and style continuity, cabin design and experience optimization, HMI design and trustworthy interaction, as well as digital twins and autonomous driving. The challenges and trends of AIGC in automotive design were discussed in relation to the industry demands of autonomous driving and human-vehicle collaboration. AIGC demonstrates significant potential in automotive design. It can enhance design efficiency and user experience, foster trust in human-machine interaction, and facilitate human-vehicle collaboration in HMI design. In the future, breakthroughs in intelligent design and further development of intelligent driving are expected to be driven by AIGC.

关键词

生成式人工智能(AIGC) / 汽车设计 / 生成式对抗网络 / 图像生成

Key words

artificial intelligence generated content (AIGC) / automotive design / generative adversarial networks / image generation

引用本文

导出引用1
许迅, 李亚军, 赵思行. AIGC赋能汽车设计的技术逻辑与未来趋势[J]. 包装工程. 2025, 46(22): 319-330 https://doi.org/10.19554/j.cnki.1001-3563.2025.22.029
XU Xun, LI Yajun, ZHAO Sixing. Technological Logic and Future Trends of AIGC Empowering Automotive Design[J]. Packaging Engineering. 2025, 46(22): 319-330 https://doi.org/10.19554/j.cnki.1001-3563.2025.22.029
中图分类号: TB472   

参考文献

[1] CHEN C, FU J, LYU L.A Pathway towards Responsible AI Generated Content[C]//Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. Macao: IJCAI Organization. 2023: 7033-7038.
[2] GUTMANN M U, HYVÄRINEN A. Extracting Coactivated Features from Multiple Data Sets[C]//Artificial Neural Networks and Machine Learning-ICANN 2011: 21st International Conference on Artificial Neural Networks. Berlin: Springer, 2011: 323-330.
[3] WEIZENBAUM J.ELIZA-a Computer Program for the Study of Natural Language Communication between Man and Machine[J]. Communications of the ACM, 1966, 9(1): 36-45.
[4] LECUN Y, BOTTOU L, BENGIO Y, et al.Gradient-based Learning Applied to Document Recognition[J]. IEEE Access, 1998, 86(11): 2278-2324.
[5] KINGMA D P, WELLING M.Auto-encoding Variational Bayes[C]//Proceedings of the ICLR 2014 Conference. Banff: ICLR. 2014.
[6] GOODFELLOW I J, POUGETu-ABADIE J, MIRZA M, et al.Generative Adversarial Nets[C]//Advances in Neural Information Processing Systems 27 (NIPS 2014). Montreal: Curran Associates, 2014: 1-9.
[7] RADFORD A, METZ L, CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks[EB/OL]. (2016-01-12) [2024-11-09]. arXiv preprint arXiv:1511.06434.
[8] ISOLA P, ZHU J Y, ZHOU T, et al.Image-to-image Translation with Conditional Adversarial Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE. 2017: 1125-1134.
[9] ZHU J Y, PARK T, ISOLA P, et al.Unpaired Image-to-image Translation Using Cycle-consistent Adversarial Networks[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice: IEEE. 2017: 2223-2232.
[10] KARRAS T, LAINE S, AILA T.A Style-Based Generator Architecture for Generative Adversarial Networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long?Beach: IEEE. 2019: 4401-4410.
[11] AJAYI E A, LIM K M, CHONG S C, et al.3D Shape Generation via Variational Autoencoder with Signed Distance Function Relativistic Average Generative Adversarial Network[J]. Applied Sciences, 2023, 13(10): 5925.
[12] ROOHI A, SHEIKHFAAL S, ANGIZI S, et al.ApGAN: Approximate GAN for Robust Low Energy Learning From Imprecise Components[J]. IEEE Transactions on Computers, 2020, 69(3): 349-360.
[13] MAO W D, YANG P X. WANG Z F.FTA-GAN: A Computation-efficient Accelerator for GANs with Fast Transformation Algorithm[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(6): 2978-2992.
[14] LI X, SU J N, ZHANG Z P, et al.Product Innovation Concept Generation Based on Deep Learning and Kansei Engineering[J]. Journal of Engineering Design, 2021, 32(10): 559-589.
[15] SURYAWATI E, PARDEDE H F, ZILVAN V, et al.Unsupervised Feature Learning-based Encoder and Adversarial Networks[J]. Journal of Big Data, 2021(8): 1-17.
[16] HONG S H, RYU S, LIM J, et al.Molecular Generative Model Based on an Adversarially Regularized Autoencoder[J]. Journal of Chemical Information and Modeling, 2019, 60(1): 29-36.
[17] GUO X R, XU S, LIN X B, et al.3D Hand Pose Estimation from a Single RGB Image through Semantic Decomposition of VAE Latent Space[J]. Pattern Analysis and Applications, 2022, 25(1): 157-167.
[18] HU H, ZHANG C, LIANG Y X.Banner Layout Retargeting with Hierarchical Reinforcement Learning and Variational Autoencoder[J]. Multimedia Tools and Applications, 2022, 81(24): 34417-34438.
[19] DING H, CUI Z M, MAGHAMI E, et al.Morphology and Mechanical Performance of Dental Crown Designed by 3D-DCGAN[J]. Dental Materials, 2023, 39(3): 320-332.
[20] CHEN Z, JIN M W, DENG Y, et al.Improvement of a Deep Learning Algorithm for Total Electron Content Maps: Image Completion[J]. Journal of Geophysical Research: Space Physics, 2019, 124(1): 790-800.
[21] HU W J, XIE T Y, LI B S, et al.An Edge Intelligence-based Generative Data Augmentation System for IoT Image Recognition Tasks[J]. Journal of Internet Technology, 2021, 22(4): 765-778.
[22] DU L, CUI Z H, WANG L F, et al.Structure Tuning Method on Deep Convolutional Generative Adversarial Network with Nondominated Sorting Genetic Algorithm II[J]. Concurrency and Computation: Practice and Experience, 2020, 32(14): 1-9.
[23] FANG W, ZHANG F H, SHENG V S, et al.A Method for Improving CNN-Based Image Recognition Using DCGAN[J]. Computers, Materials & Continua, 2018, 57(1): 167-178.
[24] RAMESH A, DHARIWAL P, NICHOL A, et al. Hierarchical Text-conditional Image Generation with Clip Latents[EB/OL].(2022-03-21)[2024-07-21].arXiv preprint arXiv:2204.06125 1.2.
[25] HO J, JAIN A, ABBEEL P.Denoising Diffusion Probabilistic Models[C]//Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020). Vancouver: Curran Associates, Inc. 2020: 6840-6851.
[26] RUSKOV M.Grimm in Wonderland: Prompt Engineering with Midjourney to Illustrate Fairytales[C]//19th Conference on Information and Research Science Connecting to Digital and Library Science. Bari: CEUR?Workshop?Proceedings, 2023: 180-191.
[27] 闻一然, 刘彦博, 董晨. 基于Stable Diffusion的AI辅助汽车零部件设计流程的研究[J]. 上海汽车, 2023(12): 39-45.
WEN Y R, LIU Y B, DONG C.Research on AI-assisted Automobile Parts Design Process Based on Stable Diffusion[J]. Shanghai Auto, 2023(12): 39-45.
[28] 红旗研发新视界. 技术领航 | 研发总院造型设计院AIGC技术创新取得突破[EB/OL]. (2023-08-29)[2024-08-09]. https://mp.weixin.qq.com/s/K1Lqi-89zVogzkU6OmgzFA.
Hongqi Develops a New Vision. Technology Leads the Way | A Breakthrough in AIGC Innovation Achieved by the Styling Design Institute of the R&D Headquarters[EB/OL]. (2023-08-29)[2024-08-09]. https://mp.weixin.qq.com/s/K1Lqi-89zVogzkU6OmgzFA.
[29] RADHAKRISHNAN S, BHARADWAJ V, MANJUNATH V, et al.Creative Intelligence-Automating Car Design Studio with Generative Adversarial Networks (GAN)[C]//International Cross-Domain Conference for Machine Learning and Knowledge Extraction. Hamburg: Springer, 2018: 160-175.
[30] NOZAWA N, SHUM H, HO E. Morishima S.Single Sketch Image Based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning[C]//Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020). Valletta: SciTePress. 2020: 179-190.
[31] MA L J, QU S R, SONG L J, et al.A Physics-Informed Generative Car-Following Model for Connected Autonomous Vehicles[J]. Entropy, 2023, 25(7): 1050.
[32] 唐贤伦, 杜一铭, 刘雨微, 等. 基于条件深度卷积生成对抗网络的图像识别方法[J]. 自动化学报, 2018, 44(5): 855-864.
TANG X L, DU Y M, LIU Y W, et al.Image Recognition With Conditional Deep Convolutional Generative Adversarial Networks[J]. Acta Automatica Sinica, 2018, 44(5): 855-864.
[33] SAGE A, AGUSTSSON E, TIMOFTE R, et al.Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt?Lake?City: IEEE. 2018: 5879-5888.
[34] 裴卉宁, 谭昭芸, 张金勇, 等. DCGAN在汽车造型设计模型中的应用[J]. 机械科学与技术, 2022, 41(10): 1567-1576.
PEI H N, TAN Z Y, ZHANG J Y, et al.Application of DCGAN to Design Model of Automobile Modeling[J]. Mechanical Science and Technology for Aerospace Engineering, 2022, 41(10): 1567-1576.
[35] ZENG S, CAI Y, ZHANG R, et al.Research on Human-Machine Collaborative Aesthetic Decision-Making and Evaluation Methods in Automotive Body Design: Based on DCGAN and ANN Models[J]. IEEE Access, 2024(12): 91575-91589.
[36] SAHA S, MENZEL S, MINKU L L, et al.Quantifying the Generative Capabilities of Variational Autoencoders for 3D Car Point Clouds[C]//Proceedings of the 2020 IEEE Symposium Series on Computational Intelligence. Canberra: IEEE, 2020: 1469-1477.
[37] SAHA S, RIOS T, MINKU L L, et al.Exploiting Generative Models for Performance Predictions of 3D Car Designs[C]//Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence. Orlando: IEEE, 2021: 1-9.
[38] LI X, XIE C, SHA Z.Part-aware Product Design Agent Using Deep Generative Network and Local Linear Embedding[C]//Proceedings of the 54th Hawaii International Conference on System Sciences. Hawaii: IEEE Computer Society, 2021: 5250-5259.
[39] OSTROSI E, BLUNTZER J B, ZHANG Z, et al.Car Style-holon Recognition in Computer-aided Design[J]. Journal of Computational Design and Engineering, 2018, 6(4): 719-738.
[40] WANG H H, CHEN C P.A Case Study on Evolution of Car Styling and Brand Consistency Using Deep Learning[J]. Symmetry, 2020, 12(12): 2074.
[41] MA L S, WU Y, LI Q N, et al.Recognition of Car Front Facing Style for Machine-Learning Data Annotation: A Quantitative Approach[J]. Symmetry-Basel, 2022, 14(6): 1181.
[42] 丁满, 袁云磊, 张新新, 等. 基于深度学习的产品色彩情感化设计[J]. 计算机集成制造系统, 2023, 29(5): 1647-1656.
DING M, YUAN Y L, ZHANG X X, et al.Product Color Emotional Design Based on Deep Learning[J]. Computer Integrated Manufacturing Systems, 2023, 29(5): 1647-1656.
[43] WU Y, MA L S, YUAN X F, et al.Human-machine Hybrid Intelligence for the Generation of Car Frontal Forms[J]. Advanced Engineering Informatics, 2023(55): 101906.
[44] CHUNG J J, KIM H J.An Automobile Environment Detection System Based on Deep Neural Network and Its Implementation Using IoT-Enabled In-Vehicle Air Quality Sensors[J]. Sustainability, 2020, 12(6): 2475.
[45] JU Y J, LIM J R, JEON E S.Prediction of AI-Based Personal Thermal Comfort in a Car Using Machine-Learning Algorithm[J]. Electronics, 2022, 11(3): 340.
[46] 高晗, 李博, 韩挺. 未来汽车人机交互系统发展趋势研究[J]. 包装工程, 2018, 39(22): 22-28.
GAO H, LI B, HAN T.Development Trend of Future Automotive HMI System[J]. Packaging Engineering, 2018, 39(22): 22-28.
[47] 孙守迁, 罗凌颖, 乔显越. AIGC赋能创新设计的新动能和新路径[J]. 艺术设计研究, 2024(2): 69-76.
SUN S Q, LUO L Y, QIAO X Y.AIGC Provides New Momentum and Pathways for Innovative Design[J]. Art & Design Research, 2024(2): 69-76.
[48] WOLF J, WIEDNER M, KARI M, et al.HMInference: Inferring Multimodal HMI Interactions in Automotive Screens[C]//13th International Conference on Automotive User Interfaces and Interactive Vehicular Applications. Leeds: Association for Computing Machinery, 2021: 230-236.
[49] HUANG C F, HUANG C Y.CVAE-GAN Emotional AI Music System for Car Driving Safety[J]. Intelligent Automation and Soft Computing, 2021, 32(3): 1939-1953.
[50] CHEN Z.An Elderly-Oriented Design of HMI in Autonomous Driving Cars Based on Rough Set Theory and Backpropagation Neural Network[J]. IEEE Access, 2024(12): 26800-26818.
[51] MORRA L, LAMBERTI F, PRATTICÓ FG, et al.Building Trust in Autonomous Vehicles: Role of Virtual Reality Driving Simulators in HMI Design[J]. IEEE Transactions on Vehicular Technology, 2019, 68(10): 9438-9450.
[52] KOO J, KWAC J, JU W, et al.Why Did My Car Just Do that? Explaining Semi-autonomous Driving Actions to Improve Driver Understanding Trust and Performance[J]. International Journal on Interactive Design and Manufacturing, 2015, 9(4): 269-275.
[53] 覃京燕, 何嘉聪. 无人驾驶车元宇宙智能座舱的场景交互设计研究[J]. 包装工程, 2023, 44(18): 67-76.
QIN J Y, HE J C.Scenario Interaction Design of Metaverse Intelligent Cockpit for Autonomous Vehicle[J]. Packaging Engineering, 2023, 44(18): 67-76.
[54] REN M, FAN J, YU C, et al.CockpitGemini: A Personalized Design Framework for Smart Vehicle Cockpits Integrating Generative Model-based Multi-agent Systems and Human Digital Twins[J]. International Journal of AI for Materials and Design, 2024, 1(3): 4-19.
[55] ORLOVA, EKATERINA V.Design Technology and AI-based Decision Making Model for Digital Twin Engineering[J]. Future Internet, 2022, 14(9): 248.
[56] LV Z, CHEN D, FENG H, et al.Digital Twins in Unmanned Aerial Vehicles for Rapid Medical Resource Delivery in Epidemics[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(12): 25106-25114.
[57] HUANG Y, ZHANG J, CHEN X, et al.From Simulation to Prediction: Enhancing Digital Twins with Advanced Generative AI Technologies[C]//2024 IEEE 18th International Conference on Control & Automation (ICCA) , 2024: 90-495.
[58] SOMEPALLI G, SINGLA V, GOLDBLUM M, et al.Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 6048-6058.
[59] LI B, WANG X, XU X, et al.Semantic-Guided Image Augmentation with Pre-trained Models[EB/OL].(2023-01-21)[2024-08-23] arXiv preprint arXiv:2302.02070. 2023, 1.
[60] 鹏系设计 XDESIGN. 第一批拥抱AI的汽车设计师, 真香了吗?[EB/OL]. (2024-07-19) [2024-08-09]. https://mp.weixin.qq.com/s/2MBUqwJBmjsRFGQfnbuq_A.
XDESIGN. Have the First Wave of Automotive Designers Embracing AI Benefited? [EB/OL]. (2024-07-19) [2024-08-09]. https://mp.weixin.qq.com/s/2MBUqwJBmjsRFGQfnbuq_A.
[61] DEB J, SAIKIA L, DIHINGIA K D, et al.ChatGPT in the Material Design: Selected Case Studies to Assess the Potential of ChatGPT[J]. Journal of Chemical Information and Modeling, 2024, 64(3): 799-811.

基金

江西省高等学校教育教学改革研究课题(JXJG-23-6-29)

PDF(2017 KB)

Accesses

Citation

Detail

段落导航
相关文章

/