Namwoo Kang

Seungyeon Shin, Dongju Shin, Namwoo Kang

Topology optimization (TO) is a method of deriving an optimal design that satisfies a given load and boundary conditions within a design domain. This method enables effective design without initial design, but has been limited in use due to high computational costs. At the same time, machine learning (ML) methodology including deep learning has made great progress in the 21st century, and accordingly, many studies have been conducted to enable effective and rapid optimization by applying ML to TO. Therefore, this study reviews and analyzes previous research on ML-based TO (MLTO). Two different perspectives of MLTO are used to review studies: (1) TO and (2) ML perspectives. The TO perspective addresses "why" to use ML for TO, while the ML perspective addresses "how" to apply ML to TO. In addition, the limitations of current MLTO research and future research directions are examined.

Seungyeon Shin, Ah-hyeon Jin, Soyoung Yoo et al.

For ensuring vehicle safety, the impact performance of wheels during wheel development must be ensured through a wheel impact test. However, manufacturing and testing a real wheel requires a significant time and money because developing an optimal wheel design requires numerous iterative processes to modify the wheel design and verify the safety performance. Accordingly, wheel impact tests have been replaced by computer simulations such as finite element analysis (FEA); however, it still incurs high computational costs for modeling and analysis, and requires FEA experts. In this study, we present an aluminum road wheel impact performance prediction model based on deep learning that replaces computationally expensive and time-consuming 3D FEA. For this purpose, 2D disk-view wheel image data, 3D wheel voxel data, and barrier mass values used for the wheel impact test were utilized as the inputs to predict the magnitude of the maximum von Mises stress, corresponding location, and the stress distribution of the 2D disk-view. The input data were first compressed into a latent space with a 3D convolutional variational autoencoder (cVAE) and 2D convolutional autoencoder (cAE). Subsequently, the fully connected layers were used to predict the impact performance, and a decoder was used to predict the stress distribution heatmap of the 2D disk-view. The proposed model can replace the impact test in the early wheel-development stage by predicting the impact performance in real-time and can be used without domain knowledge. The time required for the wheel development process can be reduced by using this mechanism.

Minyoung Jwa, Jihoon Kim, Seungyeon Shin et al.

Surrogate model-based optimization has been increasingly used in the field of engineering design. It involves creating a surrogate model with objective functions or constraints based on the data obtained from simulations or real-world experiments, and then finding the optimal solution from the model using numerical optimization methods. Recent advancements in deep learning-based inverse design methods have made it possible to generate real-time optimal solutions for engineering design problems, eliminating the requirement for iterative optimization processes. Nevertheless, no comprehensive study has yet closely examined the specific advantages and disadvantages of this novel approach compared to the traditional design optimization method. The objective of this paper is to compare the performance of traditional design optimization methods with deep learning-based inverse design methods by employing benchmark problems across various scenarios. Based on the findings of this study, we provide guidelines that can be taken into account for the future utilization of deep learning-based inverse design. It is anticipated that these guidelines will enhance the practical applicability of this approach to real engineering design problems.

Ungki Lee, Namwoo Kang

Neural network (NN) ensembles can reduce large prediction variance of NN and improve prediction accuracy. For highly nonlinear problems with insufficient data set, the prediction accuracy of NN models becomes unstable, resulting in a decrease in the accuracy of ensembles. Therefore, this study proposes a frequency distribution-based ensemble that identifies core prediction values, which are expected to be concentrated near the true prediction value. The frequency distribution-based ensemble classifies core prediction values supported by multiple prediction values by conducting statistical analysis with a frequency distribution, which is based on various prediction values obtained from a given prediction point. The frequency distribution-based ensemble can improve predictive performance by excluding prediction values with low accuracy and coping with the uncertainty of the most frequent value. An adaptive sampling strategy that sequentially adds samples based on the core prediction variance calculated as the variance of the core prediction values is proposed to improve the predictive performance of the frequency distribution-based ensemble efficiently. Results of various case studies show that the prediction accuracy of the frequency distribution-based ensemble is higher than that of Kriging and other existing ensemble methods. In addition, the proposed adaptive sampling strategy effectively improves the predictive performance of the frequency distribution-based ensemble compared with the previously developed space-filling and prediction variance-based strategies.

Seungyeon Shin, Namwoo Kang

The product design process in manufacturing involves iterative design modeling and analysis to achieve the target engineering performance, but such an iterative process is time consuming and computationally expensive. Recently, deep learning-based engineering performance prediction models have been proposed to accelerate design optimization. However, they only guarantee predictions on training data and may be inaccurate when applied to new domain data. In particular, 3D design data have complex features, which means domains with various distributions exist. Thus, the utilization of deep learning has limitations due to the heavy data collection and training burdens. We propose a bi-weighted unsupervised domain adaptation approach that considers the geometry features and engineering performance of 3D design data. It is specialized for deep learning-based engineering performance predictions. Domain-invariant features can be extracted through an adversarial training strategy by using hypothesis discrepancy, and a multi-output regression task can be performed with the extracted features to predict the engineering performance. In particular, we present a source instance weighting method suitable for 3D design data to avoid negative transfers. The developed bi-weighting strategy based on the geometry features and engineering performance of engineering structures is incorporated into the training process. The proposed model is tested on a wheel impact analysis problem to predict the magnitude of the maximum von Mises stress and the corresponding location of 3D road wheels. This mechanism can reduce the target risk for unlabeled target domains on the basis of weighted multi-source domain knowledge and can efficiently replace conventional finite element analysis.

Jihoon Kim, Namwoo Kang

Three-dimensional topology optimization (TO) is a powerful technique in engineering design, but readily usable, open-source implementations remain limited within the popular Python scientific environment. This paper introduces PyTopo3D, a software framework developed to address this gap. PyTopo3D provides a feature-rich tool for 3D TO by implementing the well-established Solid Isotropic Material with Penalization (SIMP) method and an Optimality Criteria (OC) update scheme, adapted and significantly enhanced from the efficient MATLAB code by Liu and Tovar (2014). While building on proven methodology, PyTopo3D's primary contribution is its integration and extension within Python, leveraging sparse matrix operations, optional parallel solvers, and accelerated KD-Tree sensitivity filtering for performance. Crucially, it incorporates functionalities vital for practical engineering workflows, including the direct import of complex design domains and non-design obstacles via STL files, integrated 3D visualization of the optimization process, and direct STL export of optimized geometries for manufacturing or further analysis. PyTopo3D is presented as an accessible, performance-aware tool and citable reference designed to empower engineers, students, and researchers to more easily utilize 3D TO within their existing Python-based workflows.

Sunwoong Yang, Hojin Kim, Yoonpyo Hong et al.

This study explores the potential of physics-informed neural networks (PINNs) for the realization of digital twins (DT) from various perspectives. First, various adaptive sampling approaches for collocation points are investigated to verify their effectiveness in the mesh-free framework of PINNs, which allows automated construction of virtual representation without manual mesh generation. Then, the overall performance of the data-driven PINNs (DD-PINNs) framework is examined, which can utilize the acquired datasets in DT scenarios. Its scalability to more general physics is validated within parametric Navier-Stokes equations, where PINNs do not need to be retrained as the Reynolds number varies. In addition, since datasets can be often collected from different fidelity/sparsity in practice, multi-fidelity DD-PINNs are also proposed and evaluated. They show remarkable prediction performance even in the extrapolation tasks, with $42\sim62\%$ improvement over the single-fidelity approach. Finally, the uncertainty quantification performance of multi-fidelity DD-PINNs is investigated by the ensemble method to verify their potential in DT, where an accurate measure of predictive uncertainty is critical. The DD-PINN frameworks explored in this study are found to be more suitable for DT scenarios than traditional PINNs from the above perspectives, bringing engineers one step closer to seamless DT realization.

Sumin Lee, Jihoon Kim, Namwoo Kang

Mechanisms are essential components designed to perform specific tasks in various mechanical systems. However, designing a mechanism that satisfies certain kinematic or quasi-static requirements is a challenging task. The kinematic requirements may include the workspace of a mechanism, while the quasi-static requirements of a mechanism may include its torque transmission, which refers to the ability of the mechanism to transfer power and torque effectively. In this paper, we propose a deep learning-based generative model for generating multiple crank-rocker four-bar linkage mechanisms that satisfy both the kinematic and quasi-static requirements aforementioned. The proposed model is based on a conditional generative adversarial network (cGAN) with modifications for mechanism synthesis, which is trained to learn the relationship between the requirements of a mechanism with respect to linkage lengths. The results demonstrate that the proposed model successfully generates multiple distinct mechanisms that satisfy specific kinematic and quasi-static requirements. To evaluate the novelty of our approach, we provide a comparison of the samples synthesized by the proposed cGAN, traditional cVAE and NSGA-II. Our approach has several advantages over traditional design methods. It enables designers to efficiently generate multiple diverse and feasible design candidates while exploring a large design space. Also, the proposed model considers both the kinematic and quasi-static requirements, which can lead to more efficient and effective mechanisms for real-world use, making it a promising tool for linkage mechanism design.

Jangseop Park, Namwoo Kang

Nonlinear structural analyses in engineering often require extensive finite element simulations, limiting their applicability in design optimization, uncertainty quantification, and real-time control. Conventional deep learning surrogates, such as convolutional neural networks (CNNs), physics-informed neural networks (PINNs), and fourier neural operators (FNOs), face challenges with complex non-parametric three-dimensional (3D) geometries, directionally varying loads, and high-fidelity predictions on unstructured meshes. This work presents Point-DeepONet, an operator-learning-based surrogate that integrates PointNet into the DeepONet framework. By directly processing non-parametric point clouds and incorporating signed distance functions (SDF) for geometric context, Point-DeepONet accurately predicts three-dimensional displacement and von Mises stress fields without mesh parameterization or retraining. Trained using only about 5,000 nodes (2.5% of the original 200,000-node mesh), Point-DeepONet can still predict the entire mesh at high fidelity, achieving a coefficient of determination reaching 0.987 for displacement and 0.923 for von Mises stress under a horizontal load case. Compared to nonlinear finite element analyses that require about 19.32 minutes per case, Point-DeepONet provides predictions in mere seconds-approximately 400 times faster-while maintaining excellent scalability and accuracy with increasing dataset sizes. These findings highlight the potential of Point-DeepONet to enable rapid, high-fidelity structural analyses, ultimately supporting more effective design exploration and informed decision-making in complex engineering workflows.

Jihoon Kim, Yongmin Kwon, Namwoo Kang

Generative Design (GD) has evolved as a transformative design approach, employing advanced algorithms and AI to create diverse and innovative solutions beyond traditional constraints. Despite its success, GD faces significant challenges regarding the manufacturability of complex designs, often necessitating extensive manual modifications due to limitations in standard manufacturing processes and the reliance on additive manufacturing, which is not ideal for mass production. Our research introduces an innovative framework addressing these manufacturability concerns by integrating constraints pertinent to die casting and injection molding into GD, through the utilization of 2D depth images. This method simplifies intricate 3D geometries into manufacturable profiles, removing unfeasible features such as non-manufacturable overhangs and allowing for the direct consideration of essential manufacturing aspects like thickness and rib design. Consequently, designs previously unsuitable for mass production are transformed into viable solutions. We further enhance this approach by adopting an advanced 2D generative model, which offer a more efficient alternative to traditional 3D shape generation methods. Our results substantiate the efficacy of this framework, demonstrating the production of innovative, and, importantly, manufacturable designs. This shift towards integrating practical manufacturing considerations into GD represents a pivotal advancement, transitioning from purely inspirational concepts to actionable, production-ready solutions. Our findings underscore usefulness and potential of GD for broader industry adoption, marking a significant step forward in aligning GD with the demands of manufacturing challenges.

Soyoung Yoo, Namwoo Kang

Data-driven design is emerging as a powerful strategy to accelerate engineering innovation. However, its application to vehicle wheel design remains limited due to the lack of large-scale, high-quality datasets that include 3D geometry and physical performance metrics. To address this gap, this study proposes a synthetic design-performance dataset generation framework using generative AI. The proposed framework first generates 2D rendered images using Stable Diffusion, and then reconstructs the 3D geometry through 2.5D depth estimation. Structural simulations are subsequently performed to extract engineering performance data. To further expand the design and performance space, topology optimization is applied, enabling the generation of a more diverse set of wheel designs. The final dataset, named DeepWheel, consists of over 6,000 photo-realistic images and 900 structurally analyzed 3D models. This multi-modal dataset serves as a valuable resource for surrogate model training, data-driven inverse design, and design space exploration. The proposed methodology is also applicable to other complex design domains. The dataset is released under the Creative Commons Attribution-NonCommercial 4.0 International(CC BY-NC 4.0) and is available on the https://www.smartdesignlab.org/datasets

Sanghyuk Kim, Minsik Seo, Namwoo Kang

This study proposes a neural framework that predicts 3D vehicle collision dynamics by independently modeling global rigid-body motion and local structural deformation. Unlike approaches directly predicting absolute displacement, this method explicitly separates the vehicle's overall translation and rotation from its structural deformation. Two specialized networks form the core of the framework: a quaternion-based Rigid Net for rigid motion and a coordinate-based Deformation Net for local deformation. By independently handling fundamentally distinct physical phenomena, the proposed architecture achieves accurate predictions without requiring separate supervision for each component. The model, trained on only 10% of available simulation data, significantly outperforms baseline models, including single multi-layer perceptron (MLP) and deep operator networks (DeepONet), with prediction errors reduced by up to 83%. Extensive validation demonstrates strong generalization to collision conditions outside the training range, accurately predicting responses even under severe impacts involving extreme velocities and large impact angles. Furthermore, the framework successfully reconstructs high-resolution deformation details from low-resolution inputs without increased computational effort. Consequently, the proposed approach provides an effective, computationally efficient method for rapid and reliable assessment of vehicle safety across complex collision scenarios, substantially reducing the required simulation data and time while preserving prediction fidelity.

Jiyong Kim, Sunwoong Yang, Namwoo Kang

This study introduces a novel point-wise diffusion model that processes spatio-temporal points independently to efficiently predict complex physical systems with shape variations. This methodological contribution lies in applying forward and backward diffusion processes at individual spatio-temporal points, coupled with a point-wise diffusion transformer architecture for denoising. Unlike conventional image-based diffusion models that operate on structured data representations, this framework enables direct processing of any data formats including meshes and point clouds while preserving geometric fidelity. We validate our approach across three distinct physical domains with complex geometric configurations: 2D spatio-temporal systems including cylinder fluid flow and OLED drop impact test, and 3D large-scale system for road-car external aerodynamics. To justify the necessity of our point-wise approach for real-time prediction applications, we employ denoising diffusion implicit models (DDIM) for efficient deterministic sampling, requiring only 5-10 steps compared to traditional 1000-step and providing computational speedup of 100 to 200 times during inference without compromising accuracy. In addition, our proposed model achieves superior performance compared to image-based diffusion model: reducing training time by 94.4% and requiring 89.0% fewer parameters while achieving over 28% improvement in prediction accuracy. Comprehensive comparisons against data-flexible surrogate models including DeepONet and Meshgraphnet demonstrate consistent superiority of our approach across all three physical systems. To further refine the proposed model, we investigate two key aspects: 1) comparison of final physical states prediction or incremental change prediction, and 2) computational efficiency evaluation across varying subsampling ratios (10%-100%).

Yongmin Kwon, Namwoo Kang

Generative models have attracted considerable attention for their ability to produce novel shapes. However, their application in mechanical design remains constrained due to the limited size and variability of available datasets. This study proposes a deep learning-based optimization framework specifically tailored for shape optimization with limited datasets, leveraging positional encoding and a Lipschitz regularization term to robustly learn geometric characteristics and maintain a meaningful latent space. Through extensive experiments, the proposed approach demonstrates robustness, generalizability and effectiveness in addressing typical limitations of conventional optimization frameworks. The validity of the methodology is confirmed through multi-objective shape optimization experiments conducted on diverse three-dimensional datasets, including wheels and cars, highlighting the model's versatility in producing practical and high-quality design outcomes even under data-constrained conditions.

Sunwoong Yang, Youngkyu Lee, Namwoo Kang

This study presents an enhanced multi-fidelity Deep Operator Network (DeepONet) framework for efficient spatio-temporal flow field prediction when high-fidelity data is scarce. Key innovations include: a merge network replacing traditional dot-product operations, achieving 50.4% reduction in prediction error and 7.57% accuracy improvement while reducing training time by 96%; a transfer learning multi-fidelity approach that freezes pre-trained low-fidelity networks while making only the merge network trainable, outperforming alternatives by up to 76% and achieving 43.7% better accuracy than single-fidelity training; and a physics-guided subsampling method that strategically selects high-fidelity training points based on temporal dynamics, reducing high-fidelity sample requirements by 40% while maintaining comparable accuracy. Comprehensive experiments across multiple resolutions and datasets demonstrate the framework's ability to significantly reduce required high-fidelity dataset size while maintaining predictive accuracy, with consistent superior performance against conventional benchmarks.

Sunwoong Yang, Ricardo Vinuesa, Namwoo Kang

This study addresses the critical challenge of error accumulation in spatio-temporal auto-regressive (AR) predictions within scientific machine learning models by exploring temporal integration schemes and adaptive multi-step rollout strategies. We introduce the first implementation of the two-step Adams-Bashforth method specifically tailored for data-driven AR prediction, leveraging historical derivative information to enhance numerical stability without additional computational overhead. To validate our approach, we systematically evaluate time integration schemes across canonical 2D PDEs before extending to complex Navier-Stokes cylinder vortex shedding dynamics. Additionally, we develop three novel adaptive weighting strategies that dynamically adjust the importance of different future time steps during multi-step rollout training. Our analysis reveals that as physical complexity increases, such sophisticated rollout techniques become essential, with the Adams-Bashforth scheme demonstrating consistent robustness across investigated systems and our best adaptive approach delivering an 89% improvement over conventional fixed-weight methods while maintaining similar computational costs. For the complex Navier-Stokes vortex shedding problem, despite using an extremely lightweight graph neural network with just 1,177 trainable parameters and training on only 50 snapshots, our framework accurately predicts 350 future time steps reducing mean squared error from 0.125 (single-step direct prediction) to 0.002 (Adams-Bashforth with proposed multi-step rollout). Our integrated methodology demonstrates an 83% improvement over standard noise injection techniques and maintains robustness under severe spatial constraints; specifically, when trained on only a partial spatial domain, it still achieves 58% and 27% improvements over direct prediction and forward Euler methods, respectively.

Dongeon Lee, Sunwoong Yang, Jae-Won Oh et al.

Environmental pollution and fossil fuel depletion have prompted the need for renewable energy-based power generation. However, its stability is often challenged by low energy density and non-stationary conditions. Wave energy converters (WECs), in particular, need reliable real-time wave height prediction to address these issues caused by irregular wave patterns, which can lead to the inefficient and unstable operation of WECs. In this study, we propose an AI-powered reliable real-time wave height prediction model that integrates long short-term memory (LSTM) networks for temporal prediction with deep ensemble (DE) for robust uncertainty quantification (UQ), ensuring high accuracy and reliability. To further enhance the reliability, uncertainty calibration is applied, which has proven to significantly improve the quality of the quantified uncertainty. Using real operational data from an oscillating water column-wave energy converter (OWC-WEC) system in Jeju, South Korea, the model achieves notable accuracy (R2 > 0.9), while increasing uncertainty quality by over 50% through simple calibration technique. Furthermore, a comprehensive parametric study is conducted to explore the effects of key model hyperparameters, offering valuable guidelines for diverse operational scenarios, characterized by differences in wavelength, amplitude, and period. These results demonstrate the model's capability to deliver reliable predictions, facilitating digital twin of the ocean.

Sunwoong Yang, Ricardo Vinuesa, Namwoo Kang

This study aims to overcome the limitations of conventional deep-learning approaches based on convolutional neural networks in complex geometries and unstructured meshes by exploring the potential of Graph U-Nets for unsteady flow-field prediction. We present a comprehensive investigation of Graph U-Nets, originally developed for classification tasks, now tailored for mesh-agnostic spatio-temporal forecasting of fluid dynamics. Our focus is on enhancing their performance through systematic hyperparameter tuning and architectural modifications. We propose novel approaches to improve mesh-agnostic spatio-temporal prediction of transient flow fields using Graph U-Nets, enabling accurate prediction on diverse mesh configurations. Key enhancements to the Graph U-Net architecture, including the Gaussian-mixture-model convolutional operator and noise injection approaches, provide increased flexibility in modeling node dynamics: the former reduces prediction error by 95\% compared to conventional convolutional operators, while the latter improves long-term prediction robustness, resulting in an error reduction of 86\%. We demonstrate the effectiveness of these enhancements in both transductive and inductive learning settings, showcasing the adaptability of Graph U-Nets to various flow conditions and mesh structures. This work contributes to the field of reduced-order modeling for computational fluid dynamics by establishing Graph U-Nets as a viable and flexible alternative to convolutional neural networks, capable of accurately and efficiently predicting complex fluid flow phenomena across diverse scenarios.

Jangseop Park, Namwoo Kang

In engineering design, surrogate models are widely employed to replace computationally expensive simulations by leveraging design variables and geometric parameters from computer-aided design (CAD) models. However, these models often lose critical information when simplified to lower dimensions and face challenges in parameter definition, especially with the complex 3D shapes commonly found in industrial datasets. To address these limitations, we propose a Bayesian graph neural network (GNN) framework for a 3D deep-learning-based surrogate model that predicts engineering performance by directly learning geometric features from CAD using mesh representation. Our framework determines the optimal size of mesh elements through Bayesian optimization, resulting in a high-accuracy surrogate model. Additionally, it effectively handles the irregular and complex structures of 3D CADs, which differ significantly from the regular and uniform pixel structures of 2D images typically used in deep learning. Experimental results demonstrate that the quality of the mesh significantly impacts the prediction accuracy of the surrogate model, with an optimally sized mesh achieving superior performance. We compare the performance of models based on various 3D representations such as voxel, point cloud, and graph, and evaluate the computational costs of Monte Carlo simulation and Bayesian optimization methods to find the optimal mesh size. We anticipate that our proposed framework has the potential to be applied to mesh-based simulations across various engineering fields, leveraging physics-based information commonly used in computer-aided engineering.

Seongsin Kim, Minyoung Jwa, Soonwook Lee et al.

The braking performance of the brake system is a target performance that must be considered for vehicle development. Apparent piston travel (APT) and drag torque are the most representative factors for evaluating braking performance. In particular, as the two performance factors have a conflicting relationship with each other, a multidisciplinary design optimization (MDO) approach is required for brake design. However, the computational cost of MDO increases as the number of disciplines increases. Recent studies on inverse design that use deep learning (DL) have established the possibility of instantly generating an optimal design that can satisfy the target performance without implementing an iterative optimization process. This study proposes a DL-based multidisciplinary inverse design (MID) that simultaneously satisfies multiple targets, such as the APT and drag torque of the brake system. Results show that the proposed inverse design can find the optimal design more efficiently compared with the conventional optimization methods, such as backpropagation and sequential quadratic programming. The MID achieved a similar performance to the single-disciplinary inverse design in terms of accuracy and computational cost. A novel design was derived on the basis of results, and the same performance was satisfied as that of the existing design.

Soyoung Yoo, Namwoo Kang

Studies on manufacturing cost prediction based on deep learning have begun in recent years, but the cost prediction rationale cannot be explained because the models are still used as a black box. This study aims to propose a manufacturing cost prediction process for 3D computer-aided design (CAD) models using explainable artificial intelligence. The proposed process can visualize the machining features of the 3D CAD model that are influencing the increase in manufacturing costs. The proposed process consists of (1) data collection and pre-processing, (2) 3D deep learning architecture exploration, and (3) visualization to explain the prediction results. The proposed deep learning model shows high predictability of manufacturing cost for the computer numerical control (CNC) machined parts. In particular, using 3D gradient-weighted class activation mapping proves that the proposed model not only can detect the CNC machining features but also can differentiate the machining difficulty for the same feature. Using the proposed process, we can provide a design guidance to engineering designers in reducing manufacturing costs during the conceptual design phase. We can also provide real-time quotations and redesign proposals to online manufacturing platform customers.

Seongsin Kim, Ungki Lee, Ikjin Lee et al.

In optimization of a shared autonomous electric vehicle (SAEV) system, idle vehicle relocation strategies are important to reduce operation costs and customers' wait time. However, for an on-demand service, continuous optimization for idle vehicle relocation is computationally expensive, and thus, not effective. This study proposes a deep learning-based algorithm that can instantly predict the optimal solution to idle vehicle relocation problems under various traffic conditions. The proposed relocation process comprises three steps. First, a deep learning-based passenger demand prediction model using taxi big data is built. Second, idle vehicle relocation problems are solved based on predicted demands, and optimal solution data are collected. Finally, a deep learning model using the optimal solution data is built to estimate the optimal strategy without solving relocation. In addition, the proposed idle vehicle relocation model is validated by applying it to optimize the SAEV system. We present an optimal service system including the design of SAEV vehicles and charging stations. Further, we demonstrate that the proposed strategy can drastically reduce operation costs and wait times for on-demand services.

Seowoo Jang, Soyoung Yoo, Namwoo Kang

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse topology designs, which cannot be represented by conventional parametric design approaches. Recently, data-driven topology optimization research has started to exploit artificial intelligence, such as deep learning or machine learning, to improve the capability of design exploration. This study proposes a reinforcement learning (RL) based generative design process, with reward functions maximizing the diversity of topology designs. We formulate generative design as a sequential problem of finding optimal design parameter combinations in accordance with a given reference design. Proximal Policy Optimization is used as the learning framework, which is demonstrated in the case study of an automotive wheel design problem. To reduce the heavy computational burden of the wheel topology optimization process required by our RL formulation, we approximate the optimization process with neural networks. With efficient data preprocessing/augmentation and neural architecture, the neural networks achieve a generalized performance and symmetricity-reserving characteristics. We show that RL-based generative design produces a large number of diverse designs within a short inference time by exploiting GPU in a fully automated manner. It is different from the previous approach using CPU which takes much more processing time and involving human intervention.

Sunghee Lee, Soyoung Yoo, Seongsin Kim et al.

With the advancement of self-driving technology, the commercialization of Robo-taxi services is just a matter of time. However, there is some skepticism regarding whether such taxi services will be successfully accepted by real customers due to perceived safety-related concerns; therefore, studies focused on user experience have become more crucial. Although many studies statistically analyze user experience data obtained by surveying individuals' perceptions of Robo-taxi or indirectly through simulators, there is a lack of research that statistically analyzes data obtained directly from actual Robo-taxi service experiences. Accordingly, based on the user experience data obtained by implementing a Robo-taxi service in the downtown of Seoul and Daejeon in South Korea, this study quantitatively analyzes the effect of user experience on user acceptance through structural equation modeling and path analysis. We also obtained balanced and highly valid insights by reanalyzing meaningful causal relationships obtained through statistical models based on in-depth interview results. Results revealed that the experience of the traveling stage had the greatest effect on user acceptance, and the cutting edge of the service and apprehension of technology were emotions that had a great effect on user acceptance. Based on these findings, we suggest guidelines for the design and marketing of future Robo-taxi services.

Soyoung Yoo, Sunghee Lee, Seongsin Kim et al.

Despite the approaching commercialization of robo-taxis, various anxiety factors concerning the safety of autonomous vehicles are expected to form a large barrier against consumers' use of robo-taxi services. The purpose of this study is to derive the various internal and external factors that contribute to the anxieties of robo-taxi passengers, and to propose a human-machine interface (HMI) concept to resolve such factors, by testing robo-taxi services on real, complex urban roads. In addition, a remote system for safely testing a robo-taxi in complex downtown areas was constructed, by adopting the Wizard of Oz (WOZ) methodology. From the results of our tests - conducted upon 28 subjects in the central area of Seoul - 19 major anxiety factors arising from autonomous driving were identified, and seven HMI functions to resolve such factors were designed. The functions were evaluated and their anxiety reduction effects verified. In addition, the various design insights required to increase the reliability of robo-taxis were provided through quantitative and qualitative analysis of the user experience surveys and interviews.

Namwoo Kang, Yi Ren, Fred Feinberg et al.

Visual design is critical to product success, and the subject of intensive marketing research effort. Yet visual elements, due to their holistic and interactive nature, do not lend themselves well to optimization using extant decompositional methods for preference elicitation. Here we present a systematic methodology to incorporate interactive, 3D-rendered product configurations into a conjoint-like framework. The method relies on rapid, scalable machine learning algorithms to adaptively update product designs along with standard information-oriented product attributes. At its heart is a parametric account of a product's geometry, along with a novel, adaptive "bi-level" query task that can estimate individuals' visual design form preferences and their trade-offs against such traditional elements as price and product features. We illustrate the method's performance through extensive simulations and robustness checks, a formal proof of the bi-level query methodology's domain of superiority, and a field test for the design of a mid-priced sedan, using real-time 3D rendering for an online panel. Results indicate not only substantially enhanced predictive accuracy, but two quantities beyond the reach of standard conjoint methods: trade-offs between form and function overall, and willingness-to-pay for specific design elements. Moreover -- and most critically for applications -- the method provides "optimal" visual designs for both individuals and model-derived or analyst-supplied consumer groupings, as well as their sensitivities to form and functional elements.

Sangeun Oh, Yongsu Jung, Seongsin Kim et al.

Deep learning has recently been applied to various research areas of design optimization. This study presents the need and effectiveness of adopting deep learning for generative design (or design exploration) research area. This work proposes an artificial intelligent (AI)-based design automation framework that is capable of generating numerous design options which are not only aesthetic but also optimized for engineering performance. The proposed framework integrates topology optimization and deep generative models (e.g., generative adversarial networks (GANs)) in an iterative manner to explore new design options, thus generating a large number of designs starting from limited previous design data. In addition, anomaly detection can evaluate the novelty of generated designs, thus helping designers choose among design options. The 2D wheel design problem is applied as a case study for validation of the proposed framework. The framework manifests better aesthetics, diversity, and robustness of generated designs than previous generative design methods.