Christopher McComb

NASA’s Moon to Mars campaign emphasizes the need for crews and habitat systems to operate with increasing autonomy as communication delays with Earth grow beyond 5 minutes. The digital twin framework has emerged as a promising solution to monitor, diagnose, predict, and optimize space systems, but prior aerospace applications have largely centered on system autonomy rather than crew autonomy. As a result, current approaches under-represent the interaction dynamics needed by mission control to continuously evolve procedure and accomplish mission objectives. This work introduces an Interaction Digital Twin (IDT) framework that twins the interactions between humans and systems rather than focusing only on individual entities. Built on a distributed digital twin architecture with bidirectional information flow, the framework integrates three complementary types of twins: Digital Twins for habitat systems, Human Digital Twins (HDTs) for individual crew members, and Interaction Digital Twins that capture emergent phenomena such as team cohesion, trust calibration, coordination, and adaptive autonomy. Twinning the interactions moves aspects of command and control on-board, giving crew mission-control-like capabilities even during periods of communication delay. We apply the framework to an Artemis Phase II mission scenario, demonstrating how interaction-level twinning extends system-level modeling to support cognitive workload management, information sharing, and human–autonomy teaming. By elevating interactions to first-class, inference-capable elements within the digital twin architecture, this framework bridges the gap between technical system models and the human teaming constructs essential for self-sufficient deep space exploration.

The engineering design research community has studied agentic AI systems that use Large Language Model (LLM) agents to automate the engineering design process. However, these systems are prone to some of the same pathologies that plague humans. Just as human designers, LLM design agents can fixate on existing paradigms and fail to explore alternatives when solving design challenges, potentially leading to suboptimal solutions. In this work, we propose (1) a novel Self-Regulation Loop (SRL), in which the Design Agent self-regulates and explicitly monitors its own metacognition, and (2) a novel Co-Regulation Design Agentic Loop (CRDAL), in which a Metacognitive Co-Regulation Agent assists the Design Agent in metacognition to mitigate design fixation, thereby improving system performance for engineering design tasks. In the battery pack design problem examined here, we found that the novel SRL and CRDAL systems generate designs with better performance, without significantly increasing the computational cost, compared to a plain Ralph Wiggum Loop (RWL) Further, the novel CRDAL generates designs with significantly better performance than SRL. Also, we found that the CRDAL system navigated through the latent design space more effectively than both SRL and RWL. The proposed system architectures and findings of this work provide practical implications for future development of agentic AI systems for engineering design.

The engineering design research community has studied agentic AI systems that use Large Language Model (LLM) agents to automate the engineering design process. However, these systems are prone to some of the same pathologies that plague humans. Just as human designers, LLM design agents can fixate on existing paradigms and fail to explore alternatives when solving design challenges, potentially leading to suboptimal solutions. In this work, we propose (1) a novel Self-Regulation Loop (SRL), in which the Design Agent self-regulates and explicitly monitors its own metacognition, and (2) a novel Co-Regulation Design Agentic Loop (CRDAL), in which a Metacognitive Co-Regulation Agent assists the Design Agent in metacognition to mitigate design fixation, thereby improving system performance for engineering design tasks. In the battery pack design problem examined here, we found that the novel SRL and CRDAL systems generate designs with better performance, without significantly increasing the computational cost, compared to a plain Ralph Wiggum Loop (RWL) Further, the novel CRDAL generates designs with significantly better performance than SRL. Also, we found that the CRDAL system navigated through the latent design space more effectively than both SRL and RWL. The proposed system architectures and findings of this work provide practical implications for future development of agentic AI systems for engineering design.

Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration, where adaptive systems must respond to human activities. Existing data-driven agent-based models-from rule-based to deep learning-struggle in low-data environments, limiting their practicality. This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap by reasoning about everyday activities from compact contextual cues. We adopt a retrieval-augmented prompting strategy that integrates four sources of context-temporal, spatial, behavioral history, and persona-and evaluate it on the CASAS Aruba smart-home dataset. The evaluation spans two complementary tasks: next-activity prediction with duration estimation, and multi-step daily sequence generation, each tested with various numbers of few-shot examples provided in the prompt. Analyzing few-shot effects reveals how much contextual supervision is sufficient to balance data efficiency and predictive accuracy, particularly in low-data environments. Results show that large language models exhibit strong inherent temporal understanding of human behavior: even in zero-shot settings, they produce coherent daily activity predictions, while adding one or two demonstrations further refines duration calibration and categorical accuracy. Beyond a few examples, performance saturates, indicating diminishing returns. Sequence-level evaluation confirms consistent temporal alignment across few-shot conditions. These findings suggest that pre-trained language models can serve as promising temporal reasoners, capturing both recurring routines and context-dependent behavioral variations, thereby strengthening the behavioral modules of agent-based models.

People spend the majority of their lives within built environments, whose design can profoundly influence human- and community-centered outcomes such as social capital formation, access to opportunity, public health, and resilience to disruption. Just as the built environment shapes human behavior and well-being, its design, operation, and performance can be substantially improved by better understanding how people actually use and experience space. Yet both of these goals — enhancing human benefits from built environments and improving system performance through human-aware design — are constrained by a fundamental limitation: existing computational models oversimplify human agents, equipping them with static or assumed behavioral rules that fail to reflect the dynamic, adaptive, and context-sensitive nature of real-world behavior. These simplifications undermine generalizability, limiting the ability of such models to transfer insights across scenarios or support the design of responsive, human-centered spaces. To overcome these limitations, we introduce EMPIRE ( Empirical Modeling of People in Responsive Environments ) — a data-driven, hierarchical model for predicting human spatio-temporal behavior in dynamic physical environments, with a focus on scenario-based generalizability. Driven by in-situ data, EMPIRE integrates Imitation Learning for strategic activity planning and Reinforcement Learning for generating adaptive execution policies based on interpretation of the environment and preferences. This multi-layered decomposition mirrors the cognitive structure of human decision making, enabling modularity, interpretability, and adaptability across unseen spatial configurations. To illustrate EMPIRE’s generalizability, we simulate human behavior in a social infrastructure setting (i.e., a park) by generating synthetic ground-truth trajectories that incorporate heterogeneous agent preferences, environmental dynamics, and social constraints. We conduct a systematic evaluation across six distinct park layouts using a leave-one-layout-out strategy, where models are trained on five configurations and tested on the sixth. This setup allows assessment of EMPIRE’s capacity to generalize to various unseen spatial scenarios. Experimental results demonstrate that EMPIRE successfully transfers learned behavioral patterns to new environments. • Data-driven agent-based model learns activities and preferences from in-situ data. • Hierarchical IL-GNN-RL structure mirrors human cognition for behavior simulation. • GNN learns preference-based rewards from physical, environmental, and social features. • Modular, data-driven foundation for rapid what-if built environment analysis.

Accurately capturing and explaining material handling strategies in civil engineering projects could help to increase safety, quality, timely delivery, as well as understanding the material waste caused by rework and environmental condition changes, especially when humans are highly involved in tasks with complex geometries. Workers must adapt their strategies based on the working environment’s characteristics, leading to substantial differences in strategies depending on context which drives downstream inefficiencies. A particularly challenging area is the handling of composite materials, as they require substantial manual forming which is inherently error prone. This work seeks to model and understand the composite material handling process. Specifically, this paper aims to enable a reinforcement learning (RL) agent to emulate humans’ adaptive material handling process through layup process monitoring and control strategies. The taxonomy system of edge conditions and actions in the paper contributes to the description of the module configuration and controls the RL model with a small search space. Predictions of the policies including the layup sequences and action are utilized by the students to perform a manual layup on the module. Thus, integration of machine-predicted strategies into human operations shows an example of human–machine collaboration, bridging the gap between human intuition and machine’s predictions. The mean total shear, wrinkled area, and total fold were reduced from 56.31% to 50.37%, 21.07% to 17.74%, and 23.80% to 22.66%, respectively, through human–machine collaboration. The policy can also be transferred to different module configurations in future works to enhance humans’ work to adapt to various environments.

Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration, where adaptive systems must respond to human activities. Existing data-driven agent-based models--from rule-based to deep learning--struggle in low-data environments, limiting their practicality. This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap by reasoning about everyday activities from compact contextual cues. We adopt a retrieval-augmented prompting strategy that integrates four sources of context--temporal, spatial, behavioral history, and persona--and evaluate it on the CASAS Aruba smart-home dataset. The evaluation spans two complementary tasks: next-activity prediction with duration estimation, and multi-step daily sequence generation, each tested with various numbers of few-shot examples provided in the prompt. Analyzing few-shot effects reveals how much contextual supervision is sufficient to balance data efficiency and predictive accuracy, particularly in low-data environments. Results show that large language models exhibit strong inherent temporal understanding of human behavior: even in zero-shot settings, they produce coherent daily activity predictions, while adding one or two demonstrations further refines duration calibration and categorical accuracy. Beyond a few examples, performance saturates, indicating diminishing returns. Sequence-level evaluation confirms consistent temporal alignment across few-shot conditions. These findings suggest that pre-trained language models can serve as promising temporal reasoners, capturing both recurring routines and context-dependent behavioral variations, thereby strengthening the behavioral modules of agent-based models.

Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration, where adaptive systems must respond to human activities. Existing data-driven agent-based models--from rule-based to deep learning--struggle in low-data environments, limiting their practicality. This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap by reasoning about everyday activities from compact contextual cues. We adopt a retrieval-augmented prompting strategy that integrates four sources of context--temporal, spatial, behavioral history, and persona--and evaluate it on the CASAS Aruba smart-home dataset. The evaluation spans two complementary tasks: next-activity prediction with duration estimation, and multi-step daily sequence generation, each tested with various numbers of few-shot examples provided in the prompt. Analyzing few-shot effects reveals how much contextual supervision is sufficient to balance data efficiency and predictive accuracy, particularly in low-data environments. Results show that large language models exhibit strong inherent temporal understanding of human behavior: even in zero-shot settings, they produce coherent daily activity predictions, while adding one or two demonstrations further refines duration calibration and categorical accuracy. Beyond a few examples, performance saturates, indicating diminishing returns. Sequence-level evaluation confirms consistent temporal alignment across few-shot conditions. These findings suggest that pre-trained language models can serve as promising temporal reasoners, capturing both recurring routines and context-dependent behavioral variations, thereby strengthening the behavioral modules of agent-based models.

This study introduces a novel approach to the predictive modeling of human spatial preferences in built environments, leveraging Graph Neural Networks, which provide rich representation capabilities for graph-structured data, such as spatial environments. Existing models often struggle to capture the causality or the impact of the factors that influence preferences. To bridge this gap, we propose a methodology that captures the spatial, environmental, and social characteristics of the environment—structured in a graph format—to predict human spatial preferences for various activities. As a case study, the model is trained on a synthetic data set generated to mimic real-world scenarios in a university conference room. It aims to predict the likelihood of spaces being selected for specific activities such as studying, eating, and socializing. The results demonstrate the model’s ability to incorporate multifaceted environmental and social cues into its predictions, offering insights into how preferences affect human spatial behavior.

Abstract Understanding sequential human behavior in manufacturing is essential for improving productivity, safety, and human–machine collaboration. However, little is known about how the temporal structure of these behaviors varies across time scales or how such patterns can be systematically modeled to support adaptive, human-centered manufacturing systems. This article investigates the temporal structure of human interactions involved with wire arc additive manufacturing (WAAM), which serves as a representative context for advanced manufacturing environments. Using a large-scale dataset of annotated human activity in an advanced WAAM environment, we apply generative sequential models to systematically analyze how behavioral predictability and structure vary with sampling frequencies. This analysis reveals that human behavior in WAAM is highly sequential and temporally persistent, with a small number of latent modes sufficient to describe complex workflows. We show that finer temporal resolutions capture deterministic self-transitions, while coarser resolutions uncover broader procedural patterns. These insights show the potential value of classical generative models as interpretive tools in advanced manufacturing and provide a foundation for designing adaptive manufacturing systems. Future work will extend this framework to other manufacturing contexts and explore advanced sequence modeling approaches to further understand human behavioral patterns in complex industrial environments.

With generative AI-powered design tools, designers and engineers can efficiently generate large numbers of design ideas. However, efficient exploration of these ideas requires designers to select a smaller group of potential solutions for further development. Therefore, the ability to judge and evaluate designs is critical for the successful use of generative design tools. Different design representation modalities can potentially affect designers' judgments. This work investigates how different design modalities, including visual rendering, numerical performance data, and a combination of both, affect designers' design selections from AI-generated design concepts for Uncrewed Aerial Vehicles. We found that different design modalities do affect designers' choices. Unexpectedly, we found that providing only numerical design performance data can lead to the best ability to select optimal designs. We also found that participants prefer visually conventional designs with axis-symmetry. The findings of this work provide insights into the interaction between human users and generative design systems.

not-yet-known not-yet-known not-yet-known unknown Civil infrastructure is a system through which humans inter- act with each other and their environment, making it essen- tial for community well-being. Such systems, however, de- grade over time and become less usable, either due to pro- gressive wear or abrupt damage. Therefore, it becomes nec- essary to allocate resources to maintain the infrastructure and thereby ensure the community’s well-being. However, the relationship between infrastructure condition and com- munity well-being is unclear and challenging to quantify. This is especially true in locations that are impacted by climate change or other significant forcing factors. Current compu- tational models often struggle to predict cascading nonlin- ear events that occur during system failures. This paper in- troduces a computational method to quantitatively analyze the impact of infrastructure on community well-being, com- bining agent-based modeling (ABM) and network robustness measurement. We specifically examine the town of Utqiaġvik, Alaska, where permafrost thaw due to global warming threat- ens a substantial amount of infrastructure. The results show that the breakdown of critical infrastructure progressively weak- ens community access to essential resources, leading to much lower robustness. Additionally, our simulations indicate that smaller household sizes and redundant infrastructure design prove beneficial for sustaining resource accessibility and fos- tering close social connections within the community. These insights offer valuable guidance for understanding the com- plex systems interplay among communities, infrastructure, and the environment, thereby informing strategies to build more sustainable and resilient systems in remote areas such as Utqiaġvik.

Abstract Research in design grammars has been underway for over 50 years and has demonstrated great generative power for a wide range of design and engineering domains. A key limitation, though, is the lack of support for designers to develop and computationally implement formal design grammars. We explore the potential of large language models (LLMs) to act as a collaborative grammar development partner that works with human designers and provides guidance during grammar development, as well as serving as a grammar interpreter that converts natural language descriptions of design grammars into executable python code. Methods for both interpreting previously known design grammars as well as interactively and collaboratively developing a new design grammar that is not known a priori are proposed. Three case studies, namely a truss design grammar, a half-hexagon shape grammar, and a technical process grammar, are investigated, covering string, shape, and graph grammars to explore the advantages and limitations of combining design grammars and LLMs. Finally, we position formal design grammars to be a key element for the future to expand the generative power of LLMs and enable them to become more repeatable, precise, and explainable for generative design tasks.

The capacity to predict human spatial preferences within built environments is instrumental for developing Cyber-Physical-Social Infrastructure Systems (CPSIS). A significant challenge in this domain is the generalizability of preference models, particularly their efficacy in predicting preferences within environmental configurations not encountered during training. While deep learning models have shown promise in learning complex spatial and contextual dependencies, it remains unclear which neural network architectures are most effective at generalizing to unseen layouts. To address this, we conduct a comparative study of Graph Neural Networks, Convolutional Neural Networks, and standard feedforward Neural Networks using synthetic data generated from a simplified and synthetic pocket park environment. Beginning with this illustrative case study, allows for controlled analysis of each model’s ability to transfer learned preference patterns to unseen spatial scenarios. The models are evaluated based on their capacity to predict preferences influenced by heterogeneous physical, environmental, and social features. Generalizability score is calculated using the area under the precision-recall curve for the seen and unseen layouts. This generalizability score is appropriate for imbalanced data, providing insights into the suitability of each neural network architecture for preference-aware human behavior modeling in unseen built environments.

Abstract Material selection is fundamental to the design process, as it significantly affects the cost, performance, appearance, manufacturability, and sustainability of a product. It is a complex, open-ended challenge that forces designers to continuously adapt to new information, balance diverse stakeholder demands, weigh trade-offs, and navigate uncertainties to achieve the optimal outcome. Previous studies have explored the potential of large language models (LLMs) to assist in the material selection process, with findings suggesting that LLMs could provide valuable support. However, discrepancies between LLM outputs and expert recommendations indicate the need for further research. To address the limitations of standalone LLMs, particularly their lack of reasoning and action-execution capabilities, agentic AI has been developed with enhanced functionalities. These agents integrate LLMs with external search tools, allowing them to retrieve and analyze domain-specific information, iteratively refine responses, and improve decision-making alignment with experts. This study compares standalone LLMs and agentic AI frameworks, examining how search-augmented agents can more effectively emulate expert decision-making in material selection. Our findings reveal a nonlinear relationship between model size and performance, with some models demonstrating lower proximity to human survey results and struggling to follow instructions. These insights contribute to a broader understanding of AI integration in design workflows.

Abstract Modern engineering design requires high-fidelity simulations, which can impose an enormous computational burden and slow the speed of design iteration. Data-driven up-sampling methods like physics-informed neural networks (PINNs) help reduce the computational resources required. However, machine learning model capacity and hardware limitations still pose challenges when evaluating large engineering simulations with complex physics dynamics. Recently, methods have been proposed to enforce the principle of locality in physical systems to neural network layers, allowing for concurrent inference on smaller subdomains with improved efficiency and accuracy. Based on such an idea, we extend the theory of domain decomposition to complex three-dimensional geometries using graph neural networks (GNNs). We developed a graph decomposition method to improve the training and inference efficiency of machine learning models. Super-resolution GNNs are then trained on individual subdomains distributed among GPU nodes, and during the inference phase, their predictions are combined to achieve a close to linear time reduction as the number of parallel GPUs increases. This approach significantly reduces computational overhead while maintaining simulation accuracy. The parallel nature of our method allows for scalability across available hardware resources, making it suitable for industrial applications where time constraints are critical. We validate the method performance on the design and simulation of a low-pressure bleed duct from an Airbus A350 aircraft, achieving 0.9947 in R2 metric in velocity and 0.9996 in pressure compared with high-fidelity simulations. These results demonstrate that our approach can effectively bridge the gap between computational efficiency and simulation fidelity in complex engineering design tasks.

Abstract Effective teamwork is essential for engineering design, but communication challenges can hinder collaboration. Interaction Dynamics Notation (IDN) provides a structured framework for analyzing team interactions, but its manual coding process is time-consuming and impractical for real-time applications. This study presents an AI-driven system that automatically assigns IDN symbols in real-time using a combination of automatic speech recognition and a large language model (LLM). The system was tested during a NASA design sprint, achieving 80.3% alignment with human-coded IDN classifications—comparable to human inter-rater reliability. Results highlight the model’s strengths in identifying structured conversational patterns and its challenges with context-dependent interactions like humor and idea blocking. The findings demonstrate the feasibility of real-time AI-driven IDN classification, paving the way for AI-facilitated team collaboration and feedback in engineering design teams.

Abstract Point clouds are a common representation of 3D spatial data, with applications in industries such as construction, robotics, and autonomous vehicles. However, the point cloud acquisition process often add imperfections such as outliers, noise, and warped surfaces to the structures, which can lead to issues in downstream applications that rely on that point cloud, such as classification. This paper introduces the Classification, Movement, and Pull-back (ClaMP) algorithm for general optimization-based cleanup of noisy point clouds. Importantly, we develop this algorithm with very few assumptions on geometry without access to ground truth information. We evaluate its performance across three different point clouds (with flat surfaces, curved surfaces, and a combination). For each case, we perform an extensive hyperparameter search to understand the contributions of different terms in the ClaMP loss function to the overall algorithm performance.

Abstract Parametric modeling is a critical technique in engineering design that enables the rapid generation and evaluation of candidate designs. To create parametric models, engineers need to be familiar with various Computer-Aided Design (CAD) software or have a strong grasp of at least one CAD scripting library. Modern multi-modal large language models (MLLMs) present an opportunity to automate parametric modeling, as they have shown the ability to write and execute code and also to analyze outputs such as images for further refinement. Based on these multidimensional capabilities, we propose Mechanical Engineering Design Agents (MEDA), an autonomous multi-agent framework that leverages AI agents to emulate human-like division of labor to create parametric CAD models. Our framework employs a combination of zero-shot and one-shot learning for the constituent agents, striking a balance between efficiency and accuracy. We evaluate our autonomous multi-agent framework using a dataset of 200 CAD prompts. MEDA achieves a success rate of 99% in script execution. Furthermore, we observe a minimal median point cloud distance of 0.0555 between generated and ground truth CAD models, a 56% reduction compared to prior work. Our findings demonstrate that through division of labor and effective collaboration, Artificial Intelligence (AI)-powered agents can autonomously generate more accurate CAD models relying primarily on their pre-trained knowledge. This paper highlights the significant potential of employing collaborative and dynamic multi-modal AI agents for design automation while also underscoring the current limitations of MLLMs in parametric CAD modeling. Code and data are available at : https://github.com/AnK-Accelerated-Komputing/MEDA

Abstract Collaborative design in engineering is crucial, requiring input from multiple domains. Common design representations, such as CAD models, textual descriptions, and hand sketches, influence team behaviors and dynamics, potentially affecting participation equality. Prior research suggests that design artifact modalities impact collaboration by shaping communication patterns and decision-making, thereby influencing team success. Identifying the limitations of each representation allows for better selection in different contexts. This study examines three common design representations (CAD models, textual descriptions, and hand sketches) to assess their effect on equal participation in collaborative engineering design. Metrics such as speaking time, word count, and turn-taking were analyzed to detect correlations between contribution equality and design modality. Contrary to expectations, results showed no statistical difference in team behaviors across conditions. Speaking time, word count, and turns taken remained consistent, suggesting that the choice of design representation does not impact equal participation. These findings provide valuable insights for the design community, aiding the effective use of design artifacts in collaborative settings. As product development accelerates and teams become increasingly global, understanding how design representations influence collaboration is vital for optimizing teamwork in engineering design.

Abstract Artificial Intelligence (AI) adoption is rapidly transforming industries, yet many organizations struggle to assess their readiness for AI integration. This paper introduces the Corporate AI Readiness Assessment (CARA), a tool designed to evaluate an organization’s preparedness for AI implementation across three critical dimensions: organizational readiness, workforce readiness, and technology readiness. CARA provides a structured framework that enables companies to identify strengths, gaps, and necessary actions to support AI-driven initiatives. While applicable across various industries, this assessment is particularly valuable for Small and Medium enterprises (SMEs) in manufacturing and engineering design, where resource constraints often present challenges in AI adoption. The assessment is structured as a survey, offering a scoring system that classifies organizations into four readiness categories: Emerging, Developing, Advancing, and Leading. By evaluating strategic alignment, workforce capabilities, and technological infrastructure, CARA facilitates informed decision-making for AI adoption. To demonstrate its applicability, this paper presents two case studies of organizations with different levels of AI maturity, highlighting how CARA’s insights can guide strategic planning. Future work will focus on validating CARA through broader industry applications and refining its scoring methodology. By providing a practical, scalable approach to AI readiness assessment, CARA aims to support organizations in navigating the complexities of digital transformation effectively.

Abstract The press forming process is critical for manufacturing a wide array of products from materials such as metal and glass. Each forming process requires an accurate simulation beforehand to support design optimization and to prevent defects in the actual manufacturing of high-quality products. However, traditional finite element method (FEM) simulations that are commonly used to predict deformation and stress during the forming process are computationally intensive and time-consuming. Deep learning (DL) models have emerged as a promising alternative. These machine learning models can significantly reduce computational costs and provide fast inference once trained, which makes them attractive for large-scale and real-time applications. Despite the potential of DL in simulating press forming processes, there is no comprehensive, publicly available dataset that captures variability in deformation based on different die shapes. In this work, we fill that gap by providing a detailed dataset for simulating stress and deformation in a three-dimensional space on 15 different die shapes with additional parametric variation in each shape. The dataset also features variations in mesh size and time steps, offering diverse experimentation capabilities on new models. In addition, we also deliver DL benchmarking to demonstrate the utility of the dataset. This dataset is valuable for researchers and industry practitioners looking to utilize AI/ML to efficiently simulate press forming.1

Abstract Modern engineering design increasingly relies on probabilistic simulation to account for uncertainties in geometry and loading conditions. The stochastic finite element method (SFEM) has become standard, using thousands of deterministic FEM evaluations to estimate uncertainty, creating prohibitively computational costs that inhibit efficient design exploration. Neural network (NN) surrogate models offer a promising alternative, shifting computation to a one-time upfront training cost while enabling near-instantaneous subsequent evaluations. However, effective NN surrogates for SFEM must learn to directly predict distributions that traditionally emerge from iterative sampling and aggregation of system responses across varying parameter spaces. While research has explored various NN architectures for physical simulations, their effectiveness for SFEM problems with geometric complexity and stochastic loading remains understudied, particularly for predicting physical field distributions requiring global-local feature relationship understanding. This work systematically evaluates eleven NN architectures organized into three categories: attention-based, message-passing, and hierarchical approaches. Our evaluation using 3D geometries with stochastic point elastic loading reveals that while these surrogate models achieve inference speeds orders of magnitude faster than traditional SFEM (milliseconds versus hours), their accuracy remains below the level required for full replacement in iterative design applications. Our findings identify specific architectural tradeoffs, highlighting avenues for hybrid approaches that may better balance computational efficiency with predictive accuracy.

ABSTRACT: Africa's manufacturing sector is pivotal for economic growth and technological advancement. However, challenges such as inadequate infrastructure, supply chain disruptions, geopolitical tensions, and high costs hinder its development. These issues impede domestic production and reduce global competitiveness. Addressing them is essential for economic resilience. While beneficial, traditional strategies often overlook fundamental production constraints, especially in manufacturing sectors reliant on repair, maintenance, specialized components, and tooling. Manufacturing methods like casting face limitations in flexibility, cost, precision, and lead times. This research proposes using additive manufacturing (AM)-assisted casting to address these challenges. We identify agriculture and automotive as sectors with high potential to implement AM-assisted casting.

Abstract Modern engineering design increasingly relies on probabilistic simulation to account for uncertainties in geometry and loading conditions. The stochastic finite element method (SFEM) has become standard as a way to address this need, using thousands of deterministic FEM evaluations to estimate the uncertainty. However, this creates a prohibitively high computational cost that can inhibit efficient design exploration. Neural network (NN) surrogate models offer a promising alternative, shifting computation to a one-time upfront training cost while enabling near-instantaneous subsequent evaluations for iterative design tasks. However, effective NN surrogates for SFEM must learn to directly predict distributions that traditionally emerge from iterative sampling and aggregation of system responses across varying parameter spaces. Although previous research has explored various NN architectures for physical simulations, their effectiveness specifically for SFEM problems that combine geometric complexity with stochastic loading conditions, particularly in predicting converged distribution of physical fields that require understanding relationships between global and local features, remains inadequately addressed. This work addresses this gap by systematically evaluating 11 NN architectures organized into three distinct learning mechanism categories: attention-based, message passing, and hierarchical approaches. Our evaluation using 3D geometries with stochastic point elastic loading reveals that while these surrogate models achieve inference speeds orders of magnitude faster than traditional SFEM (milliseconds versus hours for traditional SFEM), their accuracy remains below the level required for full replacement of SFEM in iterative design applications. Our findings identify specific architectural trade-offs, highlighting avenues for hybrid approaches that may better balance computational efficiency with predictive accuracy.

Abstract Multifidelity reinforcement learning (RL) frameworks significantly enhance the efficiency of engineering design by leveraging analysis models with varying levels of accuracy and computational costs. The prevailing methodologies, characterized by transfer learning, human-inspired strategies, control variate techniques, and adaptive sampling, predominantly depend on a structured hierarchy of models. However, this reliance on a model hierarchy overlooks the heterogeneous error distributions of models across the design space, extending beyond mere fidelity levels. This work proposes adaptively learned policy with heterogeneous analyses (ALPHA), a novel multifidelity RL framework to efficiently learn a high-fidelity policy by adaptively leveraging an arbitrary set of nonhierarchical, heterogeneous, low-fidelity models alongside a high-fidelity model. Specifically, low-fidelity policies and their experience data are dynamically used for efficient targeted learning, guided by their alignment with the high-fidelity policy. The effectiveness of ALPHA is demonstrated in analytical test optimization and octocopter design problems, utilizing two low-fidelity models alongside a high-fidelity one. The results highlight ALPHA's adaptive capability to dynamically utilize models across time and design space, eliminating the need for scheduling models as required in a hierarchical framework. Furthermore, the adaptive agents find more direct paths to high-performance solutions, showing superior convergence behavior compared to hierarchical agents.

Abstract The use of artificial intelligence (AI) to guide team dynamics has the potential to transform collaborative problem-solving processes. Existing approaches to doing so are trained on prior problem-specific data, limiting them to problems that have already been solved. This research aims to extend AI-based approaches to novel situations by eliminating the need for prior data. This is accomplished by focusing on team communication and collective intelligence (CI) rather than problem-specific strategies. CI is a team's general ability to work well across various tasks and is more predictive of team performance than individual intelligence. This work introduces an AI facilitator that monitors CI attributes—collective attention, equal participation, and consistent communication—in real time and intervenes as necessary to guide teams toward better collaboration and overall performance. Two human subjects studies are performed on teams working together to design a mechanical system to test the AI facilitator. The studies vary in the structure of the problem-solving environment (virtual or colocated) and communication modality (text-only or verbal). The studies' findings support that the AI facilitator leads teams to better performance than without using the facilitator, and equivalent performance when compared to a human facilitator. This contribution to the field of AI in team management is notable because of the elimination of the need for prior data, making it applicable to novel situations. This work lays the groundwork for a new approach to potentially transform the future of teamwork.

Time-dependent partial differential equations (PDEs) for classic physical systems are established based on the conservation of mass, momentum, and energy, which are ubiquitous in scientific and engineering applications. These PDEs are strictly local-dependent according to the principle of locality in physics, which means that the evolution at a point is only influenced by the neighborhood around it whose size is determined by the length of timestep multiplied with the speed of characteristic information traveling in the system. However, deep learning architecture cannot strictly enforce the local-dependency as it inevitably increases the scope of information to make local predictions as the number of layers increases. Under limited training data, the extra irrelevant information results in sluggish convergence and compromised generalizability. This paper aims to solve this problem by proposing a data decomposition method to strictly limit the scope of information for neural operators making local predictions, which is called data decomposition enforcing local-dependency (DDELD). The numerical experiments over multiple physical phenomena show that DDELD significantly accelerates training convergence and reduces test errors of benchmark models on large-scale engineering simulations.

Efficiently managing evolving data is crucial in applications like computational simulations and sensing, where dynamic data tracking and processing are essential.In simulations, the traditional method known as full-state encoding stores the entire system state, including all nested data structures and variable values, at every timestep.While simple to implement, this approach is highly storage-intensive.On the other hand, recalculating states from scratch to avoid storage demands is computationally expensive.Similarly, in sensing, continuously transmitting full data snapshots is inefficient, leading to increased bandwidth consumption and latency.KeepDelta addresses this challenge by providing a lightweight Python library that captures and applies only the changes (deltas) between successive states of complex, nested Python data structures.Designed for clarity and ease of use, KeepDelta produces human-readable outputs, facilitating debugging and analysis in research applications.

Engineering simulations generate complex multimodal data that are crucial for design iteration and validation. The interpretation of these simulations traditionally requires significant domain expertise and cognitive effort. Recently, vision-language models (VLMs) have demonstrated impressive capabilities in general-domain multimodal reasoning tasks, offering the potential for automating simulation data interpretation. However, the effectiveness of these models in specialized engineering contexts remains largely unexplored. This paper presents an initial comparative evaluation of state-of-the-art VLMs on question answering tasks involving structural and fluid dynamics simulation data across three modalities: text, images, and videos. In doing so, we introduce a domain-specific benchmark dataset comprising true/false questions testing comprehension for engineering simulations. Unlike general-purpose multimodal benchmarks, our evaluation focuses specifically on the technical interpretation of engineering simulation outputs, requiring specialized domain knowledge and physical reasoning that is absent from broader multimedia assessments. Our results demonstrate that text modality yields substantially higher performance (up to 69.2% accuracy with GPT-4o, 66.3% with LLaVA) than visual inputs (52.9-55.8%), with GPT-4o, LLaVA, and Phi-3 exhibiting the strongest capabilities for text comprehension. Models on average performed better on structural analysis tasks than fluid dynamics problems, with minimal advantage observed for native video processing over batched image approaches. However, reliability is still far below that needed for engineering applications, highlighting significant challenges in applying current VLMs to the interpretation of engineering simulations.

The transformative impact of data-driven methods, which have revolutionized fields like image and text analysis, relies on the availability of adequately large and diverse datasets. These datasets have fueled breakthroughs in deep learning, enabling the development of useful artificial intelligence (AI) tools such as ChatGPT, Gemini, Llama, and Stable Diffusion. Similarly, in engineering design, data-driven methodologies are reshaping traditional paradigms—enhancing design theory, decision-making processes, optimization strategies, and educational curricula. By facilitating faster design exploration and automation, these methods are opening new frontiers in the field. Despite these advancements, the adoption of machine-learning and data-driven approaches in engineering design faces significant hurdles, primarily due to dataset-related challenges. Key among these are the scarcity of publicly available datasets, insufficient sample sizes and feature diversity in existing datasets, and the limited integration of critical dimensions such as functional performance. Moreover, the demand for high-quality data presents a persistent hurdle, as engineering applications require datasets that are robust, comprehensive, and tailored to the complexities of design tasks.This editorial highlights a special collection of papers that share design datasets and examine the intersection of data-driven methodologies and engineering design. The selected works not only investigate novel approaches but also provide detailed discussions on the datasets employed, many of which are publicly released to encourage broader use and collaboration. These contributions span several critical areas of engineering, with topics ranging from engineering catalogs [1] and vehicle systems [2] to advanced materials [3,4] and manufacturing processes [5]. The datasets cover various domains including power systems [6], human-centered design [5,7–9], synthetic data generation [10], mechanical artifacts [11,12], and infrastructure monitoring [13]. Each dataset aims to fill a unique gap in current research and application capabilities, providing a valuable resource for future studies and developments in these fields [14,15]. For a comprehensive overview of the datasets discussed, refer to Table 1, which summarizes the application domains, data modalities, and scale of data included in this special issue.Ultimately, this special issue seeks to spark dialogue around best practices for managing, curating, publishing, and using datasets within the engineering design community. It also aims to inspire further research and development by making high-quality datasets accessible and promoting transparency in data use. The discussions and findings presented below build upon our collective experiences from this special issue and broader efforts in the field, leading us to explore in-depth the challenges and offer recommendations for future design datasets.The deployment of machine-learning and data-driven methodologies in engineering design is impeded by specific, critical barriers associated with the quality, availability, and applicability of datasets. This section discusses these barriers, providing an exploration of each and suggesting possible strategies to address them.One of the most prominent challenges is the scarcity of publicly available, high-quality datasets tailored for engineering design research. While datasets in fields like computer vision and natural language processing have flourished, e.g., ImageNet [20], MNIST [21], and KITTI [22] to name a few, engineering design often deals with highly specialized data that is not readily accessible. Data scarcity is also the consequence of costly computational simulations [16], real-world scenarios [19], or required human involvement [7]. Additionally, there is often a lack of incentives for practitioners to share proprietary data, which could significantly enhance the richness and applicability of public datasets. Quantifying design quality may involve digital twin modeling and simulation [15], which can require substantial computational resources. If real-world experiments are conducted, the setup and processing times can also be significant. Furthermore, human annotations or manual expert labeling often limit the total number of experiments. This scarcity impedes the development and validation of data-driven models for design tasks.Engineering design encompasses a wide range of domains and subdisciplines, each with its unique data characteristics and representation formats [5,18]. Datasets need to account for this diversity, capturing not only geometric information but also material properties, functional requirements, manufacturing constraints, and user preferences. As shown in Table 1, design data in itself encompasses everything from sketches to physical artifacts, including also text, images, 3D representations (point cloud, mesh, voxel, parametric), manufacturing codes, and temporal data. The parametrization of similar problems can also vary greatly, representing a challenge for unification and consistency.Furthermore, variations in target settings can result in differing performance metrics, making it difficult to conduct comparative evaluations across various design challenges. Often, efforts to standardize data representation for consistency across applications result in significant information loss too. This diversity and need for standardization present significant challenges in design data management.Including functional performance labels alongside a dataset of high-quality samples significantly enhances its value. For instance, historical geometric data for design artifacts offer insights into the design spaces and variations that have been explored. By adding functional performance metrics—such as design sensitivities that lead to more efficient parameterizations or the development of meta-models for optimization, or human evaluation results—the utility of these datasets is greatly enriched, as seen in the DeepJEB [12] and power systems datasets [6]. However, capturing this functional performance can be computationally intensive and expensive, often constrained by the capabilities and accuracy of the computational models used, such as resolution and simulation fidelity, or may require extensive human input and experimental setups. Detailed documentation of the simulation settings and constraints under which the performance data were gathered—whether through simulations, experiments, or evaluations—is essential to enhance dataset comparability and utility. This documentation not only helps in assessing the reliability of the data but also facilitates the enhancement and completion of datasets by addressing performance gaps identified after initial data collection. This challenge of capturing diverse and comprehensive performance data applies across various fields, impacting the scalability and applicability of the resulting datasets.Ensuring the quality and reliability of datasets is paramount for the trustworthiness of research findings. Design datasets may suffer from inconsistencies, errors, or biases that can undermine the validity of data-driven models. Robust data validation and cleaning processes are essential to guarantee the accuracy and consistency of datasets. Furthermore, computational simulations, such as digital twins used in engineering design and product development, play a critical role in decision-making through extensive what-if analyses and optimizations. As the fidelity and computational power of these models increase, it is crucial to maintain rigorous verification of their parameters to ensure they accurately represent real-world conditions. Common errors in simulation data that need attention include unrealistic boundary conditions, numerical inaccuracies, oversimplified assumptions in physical modeling, and errors in data integration [14]. These errors can lead to significant discrepancies between simulated outcomes and actual performance, potentially leading to flawed conclusions in downstream applications of machine learning. This underscores the need for a comprehensive approach that includes not only data collection and curation but also detailed validation against empirical data to ensure simulations provide reliable and actionable insights.The avoidance of negative effects of biased data on statistics and machine learning is a typical challenge in the generation of datasets. For example, collecting design and performance data from computationally costly optimization runs usually reflects only that small corridor of the design and search space leading to an optimal design. Hence, downstream machine-learning models may provide a high accuracy in this space but lack generalization. Also, regional influences like datasets collected in the global north can lead to inherent inequities in trained models. When collecting data it is important to apply a reasonable design sampling strategy and design of experiments to balance between a fair distribution and the number of generated data samples. Data quality checks and outlier detection need to be applied to prevent biased results as best as possible.Datasets may contain sensitive information about individuals, companies, or intellectual property. Researchers must address ethical considerations related to data privacy, ensuring that datasets are collected, stored, and shared responsibly. Understanding legal and ethical frameworks surrounding data ownership, confidentiality, and usage is essential for ethical and responsible research practices. For instance, in Ref. [9], the authors obtained informed consent from all participants and ensured that the dataset was anonymized after collection and before publication. Furthermore, industrial data can rarely be disclosed due to confidentiality concerns particularly important in engineering. Developing methods to share data without disclosing private information is essential to tap into the knowledge owned by engineering companies. Synthetic data transformation and federated learning methods could play an important role in that context.As we move from identifying challenges to proposing recommendations, it becomes apparent that addressing these barriers requires strategic action, not just technical solutions. The forthcoming recommendations, based on our discussions, aim to address many of these issues to foster the development of better, more effective datasets in engineering design research.Looking ahead, we would like to highlight important themes to continue pushing data-driven methods and datasets.Datasets should be tailored to the specific needs of the design research community, focusing on data directly relevant to tasks and challenges encountered in real-world design scenarios. Two papers that highlight this concept are DeepJEB [12] and the linkage mechanisms dataset [11]. Both of these papers discuss the importance of generating data for a specific domain, such as jet engine brackets or planar linkage mechanisms, and demonstrate how these datasets can be used to solve problems using deep learning techniques. Since data generation is usually a costly process, it is recommended to explore steps to record, calculate, and store additional data features that may be useful for future use cases.To enhance domain-relevant dataset availability, the creation of synthetic datasets is also recommended [23]. These datasets can replicate complex, real-world conditions that are often costly or impractical to capture directly. By employing large multimodal foundation models, advanced simulation tools, and diverse sampling methods, synthetic data can cover extensive design variations, operational scenarios, customer data, or functional requirements [10,24]. Validation against real-world data ensures their practical applicability for training robust models. For example, in Ref. [16], the authors compared car drag coefficients obtained from simulations at three different mesh resolutions with experimental values and reference simulations. Such efforts are crucial in areas where experimental data are scarce or difficult to obtain, thereby supporting the development of predictive models and AI-driven design tools.In engineering design applications, the credibility of data hinges significantly on design context, such as how well boundary conditions, solver settings, and modeling assumptions mirror real-world scenarios. It is crucial for authors to meticulously detail the conditions under which each dataset was generated—be it through physical experiments, simulations, or a combination of methods—and include any cross-validation or calibration steps undertaken. This vital contextual information not only aids researchers in assessing the dataset’s relevance and suitability for their specific needs but also highlights discrepancies between simulated outcomes and actual performance.Simulation data are abundant in engineering design (e.g., aerodynamics, power grids, manufacturing), but purely simulated datasets may not fully capture real-world behavior. Including a “validation tier” or smaller subset of real-world measurements—such as wind tunnel tests for aerodynamic models—helps quantify the gap between simulated and actual performance. Several papers [6,16] in the special issue emphasize the significance of explicitly outlining the simulation methods and providing the necessary information for users to rerun or modify simulations. When multifidelity data (low-/mid-/high-fidelity simulations) are available, clearly indicate the conditions and solver settings for each tier, allowing future users to match their own fidelity requirements and assess downstream accuracy.Additionally, engineering datasets should comprehensively encode specific constraints (e.g., material limits, safety margins, regulatory requirements) and objectives (e.g., cost, weight, performance). Clearly articulating these constraints and objectives, beyond mere geometric or operational parameters, renders the datasets more directly useful for optimization and decision-making processes [4]. For instance, specifying allowable stress ranges or mandated design codes enables researchers to evaluate constraint-handling strategies and foster realistic, applicable design solutions. This integrated approach ensures that datasets are both deeply informative and highly applicable across various design scenarios.With the advancements in algorithms and computational power, machine-learning models are capable of learning data of higher complexity, dimensionality, and multimodal characteristics. Research such as Ref. [14] demonstrates that integrating diverse data sources enhances model accuracy. Researchers and practitioners should seize opportunities to identify and incorporate additional features or performance indicators that extend beyond the current core application target. Balancing the data to avoid outliers or biases by applying state-of-the-art design of experiment methods will further increase the value of the dataset for various downstream data science tasks [3]. In addition, rich datasets also motivate researchers and scientists to extend existing methods and develop new models to broaden the application spectrum. We recommend adopting open-access practices for nonproprietary data and encouraging collaboration across research domains to overcome data scarcity and enhance dataset diversity. Following the lead of existing design data repositories,1,2 we encourage researchers and institutions to establish and support similar platforms. This approach promotes wider data access and fosters a culture of shared innovation within the research community.Another recommendation is to balance granularity and dataset size for surrogate modeling [15]. High-resolution simulations generate massive datasets (e.g., millions of mesh nodes in computational fluid dynamics or finite element analysis). While these data can train powerful surrogate models, storing every simulation output may be impractical. Guidance should be provided on how each subset or “downsampled” version (e.g., coarser meshes, aggregated performance metrics) can be utilized for scaled analysis, and it should be clarified how closely they track the high-resolution truth. This ensures that others can choose the right balance of granularity and computational feasibility for their needs.In engineering design, capturing data throughout the entire process—from initial concept through to operational stages—is crucial. Several papers in this issue highlight data from human-centered activities such as team-based hackathons [9], user interviews [7], and collaborative assembly tasks [5], underscoring the importance of documenting not just the final design artifact but also the process itself. This includes key decision points, intermediate prototypes, and user feedback, providing a comprehensive view that enhances our understanding of collaborative design behaviors, design thinking strategies, and empathic accuracy. Similarly, for products like power grids [6], wind turbines [13], and manufacturing lines [5] that span multiple design, production, and operational stages, it is beneficial to link datasets from upstream decisions (e.g., conceptual choices) to downstream impacts (e.g., maintenance records, quality metrics). By ensuring data continuity through consistent component identifiers or timestamps, researchers can easily integrate and explore these sources, supporting robust life-cycle analyses and design methods. Collectively, these practices not only enrich the data’s detail and applicability but also facilitate a more holistic understanding of the entire design and production life-cycle.Many articles introduce specialized datasets (e.g., CAD design [18], mechanical metamaterials [3], linkage mechanisms [11]). Support for fair comparison and acceleration of progress can be enhanced by specifying baseline tasks (e.g., standard optimization problems, regression, and classification tasks) and performance metrics. Providing baseline results—such as recommended customer segmentation metrics [8,17]—along with dataset test and train splits, helps researchers quickly gauge whether new algorithms outperform the current state of the art.Adhering to the Findable, Accessible, Interoperable, and Reusable is essential for datasets, as in several studies consistent formats (e.g., or and clearly is critical for promoting and across design research For instance, the authors of the power systems dataset provide all the information required to power which researchers to rerun the after of the data. In addition, applying version like and researchers to specific dataset and track (e.g., or also helps foster broader and clearly any to intellectual or confidentiality with the a comprehensive documentation should be a detailed of the experimental setup and process The most valuable datasets are that provide on their applications, and any assumptions that impact their For instance, the wind dataset this by of the and which are accessible not only in the but also on the wind and in a This is relevant for design applications where simulation from real-world behavior. or that data and can significantly the to This information using the setup and also with different but similar settings, e.g., using a different simulation While detailed documentation was explicitly required for this special we the papers an for making this the in the design a final we for the documentation of datasets. and datasets in engineering design is a significant that it can be utilized further is an important to this across the community. by the for Datasets as in Ref. [16], we this to engineering design ensuring that all datasets are by detailed documentation that their and use. on the specific characteristics of our community, we that the be to the of datasets was the dataset the dataset the creation of the the that the dataset many are there in data each there any If how is the data associated with each was the data was in the data collection process (e.g., was the data was it which data to and which to any or labeling of the data (e.g., how was this and by tasks in engineering design is the dataset the dataset been used for any tasks If which performance metrics are relevant for assessing tasks using this is the dataset (e.g., there any or on its is the of availability for the dataset as provided by the is responsible for dataset can or there a in If is availability of and high-quality datasets is a to data-driven methods, including machine learning, for engineering design. In to novel data-driven approaches for various engineering domains, the research articles to this special issue provide detailed discussions on the datasets employed, the required to overcome the challenges of dataset and application within design research. to fields, this for the design and of such datasets to an of the research process by and practices tailored to the specific needs of engineering design research. with this special we to the and of datasets as contributions of their Data not only for the validation of results and collaboration with but it also fosters future across multiple this for the adoption of best practices and ethical data privacy, and data to foster dataset creation and between all We that this special issue the the challenges the design and of datasets and their role in the engineering design research We also that we have further research and development of data-driven and machine-learning methods to engineering would like to for the for and valuable on the We also our to for and input at every of this special are of data, models, or were generated or used for this

Abstract A deep understanding of manufacturing processes is essential for advancing manufacturing-oriented design and engineering complex systems. As advanced manufacturing technologies evolve, systems have grown more complex, and human interaction has become a vital component of both operation and design. This shift introduces new challenges as human roles within these systems extend beyond traditional boundaries and are not yet fully understood in current design processes. Characterizing human interactions within manufacturing systems is therefore critical to supporting further advancements. Additionally, human behavior plays a significant role in many engineered systems beyond manufacturing, underscoring the value of developing methodologies to better analyze human behavior and interactions within complex environments. These methodologies can broadly support and enhance diverse aspects of engineering design. This study presents HM-SYNC, which is a comprehensive dataset of human interactions with advanced manufacturing machinery, specifically a wire-arc additive manufacturing machine. Depth images and 3D skeleton joints are collected over 6 months using privacy-preserving pose tracking with depth cameras. HM-SYNC includes thousands of interactions across various contexts, goals, and users, providing valuable insights into patterns of human–machine interaction. By capturing a diverse range of interactions in natural settings, this dataset supports advancements in human-centered manufacturing design and facilitates the development of more effective manufacturing systems. This dataset can enhance models and digital twins of manufacturing systems, help operators optimize machinery use and efficiency, and guide designers in refining machine and system design, to name just a few applications.

Abstract This paper introduces the HyForm uncrewed vehicle engineering repository (HUVER), a comprehensive multi-modal dataset of uncrewed aerial vehicle (UAV) designs, complete with performance evaluations, derived from the HyForm UAV design testbed. The dataset includes 6051 unique UAV configurations, each represented using strings adhering to a designed grammar, images, 3D mesh models, and textual descriptions, alongside performance metrics obtained from physics-based simulations. Designed to support data-driven and artificial intelligence (AI)-driven design processes, one area in which this dataset can facilitate research is the surrogate modeling and generative design of UAVs, providing a resource for developing predictive models and supporting human–AI collaboration in UAV design. The dataset adheres to findable, accessible, interoperable, and reusable principles, ensuring it is retrievable, accessible, interoperable, and reusable, and is made available as an online repository for ease of use by the research community.

Infrastructure provides an intricate system through which humans interact with each other and their environment, which is essential for community well-being. These systems, however, degrade over time and become less usable, either due to wear or abrupt damage. Therefore, it becomes necessary to allocate resources to maintain the infrastructure and ensure the community's well-being. However, the relationship between infrastructure expenditures and community well-being is unclear and challenging to measure. This is especially true in locations like Utqiagvik, Alaska, where permafrost thaw due to global warming threatens a substantial amount of infrastructure. Current computational models are inadequate for predicting the cascading effects of system failures, particularly under extreme environmental conditions. This paper introduces agent-based modeling (ABM) as a more adaptive and insightful method to study the impact of infrastructure on community well-being. This approach provides a detailed analysis of component contributions to system robustness, identifying key vulnerabilities for prioritized maintenance and resource allocation.

Abstract Collaborative engineering design is increasingly important for modern engineering practices as projects routinely require collaboration across multiple domains. Reaching shared understanding within the team is a critical factor in constructing a successful and enjoyable collaboration. One way to promote shared understanding is through the use of design artifacts and design representations as boundary objects. Different design representations have unique characteristics that benefit the engineering design process but could also hinder the development of shared understanding. It is important to identify the limitations of the design artifacts to select the suitable design artifact for the situation and mitigate potential adverse effects, including design fixation and miscommunication. Despite previous studies’ findings, there are still unsolved questions regarding the exact effect of the modality of the design representations on the development of team-shared understanding. This work examines three types of commonly used design representations in the engineering design community, namely, textual description, hand sketch and engineering CAD model. Their unique effect on the development of shared understanding is investigated in a collaborative engineering design setting. The results indicate that the modality of the design artifact would affect the development of shared understanding, and using visual representations can yield better team outcomes regardless of the modality complexity, mainly for design structures. This work shows the importance of using the proper design representation in collaborative engineering design tasks, and such a finding is a critical and timely reminder in the current age when team interactions constantly involve text-dominant online communications.