Jonathan Cagan

• Carnegie Mellon University

Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-trainin...

Recent advances in computer-aided design tools have helped rapidly advance the development of wireframe DNA origami nanostructures. Specifically, automated tools now exist that can convert an input polyhedral mesh into a DNA origami nanostructure, greatly reducing the design difficulty for wireframe DNA origami nanostructures. However, one limitati...

Composed of individual unit cells strategically arranged to achieve a desired function, lattices are a promising solution for laser powder bed fusion (LPBF) support structure design. Despite their many advantages (e.g., multifunctionality and reduced material cost), prior work in lattice support structure (LSS) design primarily focused on parts wit...

When designed effectively, support structures play a critical role to dissipate heat and mitigate part distortion without driving up excessive costs within the additive manufacturing metals technique of Laser Powder Bed Fusion (LPBF). Lattices, composed of individual unit cells strategically arranged to achieve a desired function, are a promising s...

Composed of individual unit cells strategically arranged to achieve a desired function, lattices are a promising solution for laser powder bed fusion (LPBF) support structure design in additive manufacturing. Despite their many advantages (e.g., multifunctionality and reduced material cost), prior work in lattice support structure design primarily...

A significant number of medical errors are surgical, when patients are in the operating room, and are also a prominent cause of death. Prior work introduced a Mixed Reality Combination System (MRCS) that integrates Augmented Reality (AR) technology, an inertial measurement unit (IMU) sensor, and 3D-printed, collagen-based specimens to enable realis...

A novel approach for computational agents to learn proficient behavior in engineering configuration design that is inspired by human learning is introduced in this work. The Learning Proficient Simulated Annealing Design Agents (LPSADA) begin as different proficiency designers and are explicitly modeled to mimic the design behavior and performance...

Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is dependently bounded by the need for abundant training data. Representation learning, particularly through pre-trainin...

Recent advances in artificial intelligence (AI) enable AI agents to go beyond simply supporting human activities and, instead, take more control in team decision-making. While significant literature has studied human-AI collaboration through the lens of AI as a "second opinion system," this type of interaction is not fully representative of many hu...

The Research Journey Map is introduced to guide researchers on creating engaging, meaningful and impactful presentations and publications. Built on the foundational work of the Hero's Journey by Joseph Campbell, this template helps technical researchers communicate information, data, systems and artifacts that result from research so that audiences...

As artificial intelligence (AI) systems become increasingly capable of performing design tasks, they are expected to be deployed to assist human designers' decision-making in a greater variety of ways. For complex design problems such as those with multiple objectives, one AI may not always perform its expected accuracy due to the complexity of dec...

Exploring the opportunities for incorporating Artificial Intelligence (AI) to support team problem solving has been the focus of intensive ongoing research. However, while the incorporation of such AI tools into human team problem solving can improve team performance, it is still unclear what modality of AI integration will lead to a genuine human-...

In recent years, the field of structural DNA nanotechnology has advanced rapidly due to transformative design tools. Although these tools have been revolutionary, they still bear one overall limitation of requiring users to fully conceptualize their designs before designing. Recently, a simple computational casting technique was developed using gen...

Exploring the opportunities for incorporating Artificial Intelligence (AI) to support team problem solving has been the focus of intensive ongoing research. However, while the incorporation of such AI tools into human team problem solving can improve team performance, it is still unclear what modality of AI integration will lead to a genuine human-...

Continuous constraint satisfaction is prevalent in many science and engineering fields. When solving continuous constraint satisfaction problems, it is more advantageous for practitioners to derive all feasible regions (i.e., the solution space) rather than a limited number of solution points, since these feasible regions facilitate innovative desi...

In recent years, the field of structural DNA nanotechnology has advanced rapidly due to transformative design tools. Although these tools have been revolutionary, they still bear one overall limitation of requiring users to fully conceptualize their designs before designing. Recently, a simple computational casting technique was developed using gen...

When designed effectively, support structures for Laser Powder Bed Fusion (LPBF) quickly dissipate heat and mitigate part distortion without driving up excessive costs. Lattices, composed of individual unit cells strategically arranged to achieve a desired function, are a promising solution as support structure. Prior research utilizing gradient-ba...

Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, stylistic features such as aesthetics and semantic attributes are hard to codify even for experts. As such, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challe...

Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challenging nature of design describability. This paper proposes an AI-driven method to fully automate the discove...

Continuous constraint satisfaction is prevalent in many science and engineering fields. When solving continuous constraint satisfaction problems, it is more advantageous for practitioners to derive all feasible regions (i.e., the solution space) rather than a limited number of solution points, since these feasible regions facilitate design concept...

This work introduces the Proficient Simulated Annealing Design Agent Model (PSADA), a cognitively inspired, agent-based model of engineering configuration design. PSADA models different proficiency agents using move selection heuristics and problem space search strategies, both of which are identified and extracted from prior human subject studies....

The evolution of Artificial Intelligence (AI) and Machine Learning (ML) enables new ways to envision how computer tools will aid, work with, and even guide human teams. This paper explores this new paradigm of design by considering emerging variations of AI-Human collaboration: AI used as a design tool versus AI employed as a guide to human problem...

Set-based concurrent engineering (SBCE), a process that develops sets of many design candidates for each subproblem throughout a design project, proposes several benefits compared to point-based processes, where only one design candidate for each subproblem is chosen for further development. These benefits include reduced rework, improved design qu...

Incorporating style-related objectives into shape design has been centrally important to maximize product appeal. However, stylistic features such as aesthetics and semantic attributes are hard to codify even for experts. As such, algorithmic style capture and reuse have not fully benefited from automated data-driven methodologies due to the challe...

One degree of freedom (1DOF) linkages are persistent in mechanical systems. However, designing linkages to follow a desired path, known as path synthesis, is challenging due to non-linearities, combinatorial nature, and strict geometric constraints. Current state-of-the-art algorithms cannot scale well to linkages with higher-order linkage graphs....

Successful surgical operations are characterized by preplanning routines to be executed during actual surgical operations. To achieve this, surgeons rely on the experience acquired from the use of cadavers, enabling technologies like virtual reality (VR) and clinical years of practice. However, cadavers, having no dynamism and realism as they lack...

The data are collected from a human subjects study in which 100 participants solve chess puzzle problems with AI assistance. The participants are assigned to one of the two experimental conditions determined by the direction of the change in AI performance at problem 20: 1) high- to low-performing and 2) low- to high-performing. The dataset contain...

Teams are common throughout engineering practice and industry when solving complex, interdisciplinary problems. Previous works in engineering problem solving have studied the effectiveness of teams and individuals, showing that in some circumstances, individuals can outperform collaborative teams working on the same task. The current work extends t...

Advances in artificial intelligence (AI) offer new opportunities for human-AI cooperation in engineering design. Human trust in AI is a crucial factor in ensuring an effective human-AI cooperation, and several approaches to enhance human trust in AI have been explored in prior studies. However, it remains an open question in engineering design whet...

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior data limits us only to solve problems that have been solved before and biases data-driven learning towards ex...

Important for many science and engineering fields, meaningful nonlinear models result from fitting such models to data by estimating the value of each parameter in the model. Since parameters in nonlinear models often characterize a substance or a system (e.g., mass diffusivity), it is critical to find the optimal parameter estimators that minimize...

Advances in artificial intelligence (AI) offer new opportunities for human-AI collaboration in engineering design. Human trust in AI is a crucial factor in ensuring an effective human -AI collaboration, and several approaches to enhance human trust in AI have been suggested in prior studies. However, it remains an open question in engineering desig...

This paper describes the results of an agenda-setting panel session that took place at the 2021 International Design Engineering Technical Conferences organized by the Design Theory and Methodology (DTM) research community. While the state of design research in engineering design has advanced tremendously in the last thirty-five years since the for...

Teams are common throughout engineering practice and industry when solving complex, interdisciplinary problems. Previous works in engineering problem solving have studied the effectiveness of teams and individuals, showing that in some circumstances, individuals can outperform collaborative teams working on the same task. The current work extends t...

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior data limits us only to solve problems that have been solved before and biases us towards existing solutions....

The structural design and additive manufacturing (AM) of cross-flow heat exchangers (HXs) are studied. A unit-based design framework is proposed to optimize the channel configuration in order to improve heat exchange performance (HXP) and meanwhile control pressure drop (PD) between the fluid inlet and outlet. A gradient-based optimization methodol...

Decision-making assistance by artificial intelligence (AI) during design is only effective when human designers properly utilize AI input. However, designers often misjudge the AI’s and/or their own ability, leading to erroneous reliance on AI and therefore bad designs. To avoid such outcomes, it is critical to understand the evolution of designers...

A cognitively inspired, agent-based model of engineering design proficiency is introduced in this work. Proficiency is modeled using move selection heuristics and problem space search strategies, both of which were extracted from a prior human subjects study. Agent behavior in the Proficient Simulated Annealing Design Agents (PSADA) Model is valida...

Building an AI agent that can design on its own has been a goal since the 1980s. Recently, deep learning has shown the ability to learn from large-scale data, enabling significant advances in data-driven design. However, learning over prior data limits us only to solve problems that have been solved before and biases us towards existing solutions....

Managing the design process of teams has been shown to considerably improve problem-solving behaviors and resulting final outcomes. Automating this activity presents significant opportunities in delivering interventions that dynamically adapt to the state of a team to reap the most impact. In this work, an Artificial Intelligence (AI) agent is crea...

Decision-making assistance by artificial intelligence (AI) during design is only effective when human designers properly utilize the AI input. However, designers often misjudge the AI’s and/or their own ability, leading to erroneous reliance on AI and therefore bad designs occur. To avoid such outcomes, it is crucial to understand the evolution of...

Recent advances in artificial intelligence (AI) enable researchers to create more powerful AI agents that are becoming competent teammates for humans. However, human distrust of AI is a critical factor that may impede human-AI cooperation. Although AI agents have been endowed with anthropomorphic traits, such as a human-like appearance, in prior st...

The structural design and additive manufacturing (AM) of cross-flow heat exchangers (HXs) are studied. A unit-based design framework is proposed to optimize the channel configuration in order to improve heat exchange performance (HXP) and meanwhile control pressure drop (PD) between the fluid inlet and outlet. A gradient-based optimization methodol...

This brief extends prior research by the authors on studying the impacts of interventions provided by either a human or an artificial intelligent (AI) process manager on team behaviors. Our previous research found that this AI process manager matched the capabilities of human process management. Here, this data is further studied to identify the im...

This work studies the perception of the impacts of AI and human process managers during a complex design task. Although performance and perceptions by teams that are AI- versus human-managed are similar, we show that how team members discern the identity of their process manager (human/AI), impacts their perceptions. They discern the interventions...

For successful human-artificial intelligence (AI) collaboration in design, human designers must properly use AI input. Some factors affecting that use are designers’ self-confidence and competence and those variables' impact on reliance on AI. This work studies how designers’ self-confidence before and during teamwork and overall competence are ass...

Important for many science and engineering fields, meaningful nonlinear models result from fitting such models to data by estimating the value of each parameter in the model. Since parameters in nonlinear models often characterize a substance or a system (e.g., mass diffusivity), it is critical to find the optimal parameter estimators that minimize...

Purpose This study aims to gain a deeper understanding of the industry practice to guide the formation of support tools with a rigorous theoretical backing. Cross-functional teams are an essential component in new product development (NPD) of complex products to promote comprehensive coverage of product design, marketing, sales, support as well as...

Important for many science and engineering fields, meaningful nonlinear models result from fitting such models to data by estimating the value of each parameter in the model. Since parameters in nonlinear models often characterize a substance or a system (e.g., mass diffusivity), it is critical to find the optimal parameter estimators that minimize...

Advances in artificial intelligence (AI) offer new opportunities for human-AI collaboration in engineering design. Human trust in AI is a crucial factor in ensuring an effective human -AI collaboration, and several approaches to enhance human trust in AI have been suggested in prior studies. However, it remains an open question in engineering desig...

Although necessary for complex problem solving, such as engineering design, team agility is often difficult to achieve in practice. The evolution of Artificial Intelligence (AI) affords unique opportunities for supporting team problem solving. While integrating assistive AI agents into human teams has at times improved team performance, it is still...

Surgical planning to visualize a complete procedure before surgical intervention, paired with the advanced surgical techniques of a surgeon, has been shown to improve surgical outcomes. Efforts to improve surgical planning have included tracking real-time surgeon movements via surgical instruments in a confined body cavity space in the human body t...

Despite the potential of design constraints to benefit creative processes like ideation, the relationship between constraints and ideation outcome is still not sufficiently understood in order for constraints to be implemented as a design tool. This study aims to explore the impact of specifically item constraints on the effectiveness of ideation b...

Human subject experiments are performed to evaluate the influence of artificial intelligence (AI) process management on human design teams solving a complex engineering problem and compare that to the influence of human process management. Participants are grouped into teams of five individuals and asked to generate a drone fleet and plan routes to...

As machine learning is used to make strides in med- ical diagnostics, few methods provide heuristics from which human doctors can learn directly. This work introduces a method for leveraging human observable structures, such as macro scale vascular formations, for producing assessments of medical conditions with rela- tively few training cases, and...

Engineering design problems often involve large state and action spaces along with highly sparse rewards. Since an exhaustive search of those spaces is not feasible, humans utilize relevant domain knowledge to condense the search space. Previously, deep learning agents (DLAgents) were introduced to use visual imitation learning to model design doma...

Generative design problems often encompass complex action spaces that may be divergent over time, contain state-dependent constraints, or involve hybrid (discrete and continuous) domains. To address those challenges, this work introduces Design Strategy Network (DSN), a data-driven deep hierarchical framework that can learn strategies over these ar...

Generative design problems often encompass complex action spaces that may be divergent over time, contain state-dependent constraints, or involve hybrid (discrete and continuous) domains. To address those challenges, this work introduces Design Strategy Network (DSN), a data-driven deep hierarchical framework that can learn strategies over these ar...

Managing the design process of teams has been shown to considerably improve problem-solving behaviors and resulting final outcomes. Automating this activity presents significant opportunities in delivering interventions that dynamically adapt to the state of a team in order to reap the most impact. In this work, an Artificial Intelligent (AI) agent...

Artificial intelligence (AI) has shown its promise in assisting human decision-making. However, humans' inappropriate decision to accept or reject suggestions from AI can lead to severe consequences in high-stakes AI-assisted decision-making scenarios. This problem persists due to insufficient understanding of human trust in AI. Therefore, this res...

Human subject experiments are often used in research efforts to understand human behavior in design. However, such research is often time-consuming, expensive, and limited in scope due to the need to experimentally control specific variables. This work develops an initial digital simulation of team-based multidisciplinary design, where the actions...

As Artificial Intelligence (AI) assistance tools become more ubiquitous in engineering design, it becomes increasingly necessary to understand the influence of AI assistance on the design process and design effectiveness. Previous work has shown the advantages of incorporating AI design agents to assist human designers. However, the influence of AI...

Creative problem solving is often conceptualised as a process of search. However, little is known about the difficulties of carrying out this search process. We conducted three studies examining how strongly different task characteristics impact creative problem-solving performance. In Study 1, regression analyses on normative data of Remote Associ...

Human-artificial intelligent (AI) - assisted teaming is becoming a strategy for coalescing the complementary strengths of humans and computers to solve difficult tasks. Yet, there is still much to learn regarding how the integration of humans with AI agents into a team affects human behavior. Accordingly, this work begins to inform this research ga...

As Artificial Intelligence (AI) assistance tools become more ubiquitous in engineering design, it becomes increasingly necessary to understand the influence of AI assistance on the design process and design effectiveness. Previous work has shown the advantages of incorporating AI design agents to assist human designers. However, the influence of AI...

Engineering design problems often involve large state and action spaces along with highly sparse rewards. Since an exhaustive search of those spaces is not feasible, humans utilize relevant domain knowledge to condense the search space. Deep learning agents (DLAgents) were previously introduced to use visual imitation learning to model design domai...

The design of visual interfaces plays a crucial role in ensuring swift and accurate information search for operators, who use procedures and information tables to cope with problems arising during emergencies. The primary cognitive mechanism involved in information search is visual attention. However, design of interfaces is seldom done through app...

Through experience, designers develop guiding principles, or heuristics, to aid decision-making in familiar design domains. Generalized versions of common design heuristics have been identified across multiple domains and applied by novices to design problems. Previous work leveraged a sample of these common heuristics to assist in an agent-based d...

Computationally studying team discourse can provide valuable, real-time insights into the state of design teams and design cognition during problem-solving. The particular experimental design, adopted from previous work by the authors, places one of the design team conditions under the guidance of a human process manager. In that work, teams under...

Featured Application A first demonstration of a shape annealing algorithm for automatic generation of DNA origami designs based on defined objectives and constraints. Abstract Structural DNA nanotechnology involves the design and self-assembly of DNA-based nanostructures. As a field, it has progressed at an exponential rate over recent years. The...

Human subject experiments are performed to assess the impact of artificial intelligence (AI) agents on distributed human design teams and individual human designers. In the team experiment, participants in teams of six develop and operate a drone fleet to deliver parcels routed to multiple locations of a target market. Among the design teams in the...

Recent advances in artificial intelligence (AI) offer opportunities for integrating AI into human design teams. Although various AIs have been developed to aid engineering design, the impact of AI usage on human design teams has received scant research attention. This research assesses the impact of a deep learning AI on distributed human design te...

Products must often endure challenging conditions while fulfilling their intended functions. Game-theoretic methods can readily create a wide variety of these conditions to consider when creating designs. This work introduces Cognitively Inspired Adversarial Agents (CIAAs) that use a Stackelberg game format to generate designs resistant to these co...

Advances in artificial intelligence create new opportunities for computers to support humans as peers in hybrid teams in several complex problem-solving situations. This paper proposes a decision-making architecture for adaptively informing decisions in human-computer collaboration for large-scale competitive problems under dynamic environments. Th...

Prior research has demonstrated how the average characteristics of a team impact team performance. The relative contribution of team members has been largely ignored, especially in the context of engineering design. In this work, a behavioral study was conducted to uncover whether the most or least proficient member of a configuration design team h...

Fitting a specified model to data is critical in many science and engineering fields. A major task in fitting a specified model to data is to estimate the value of each parameter in the model. Iterative local methods, such as the Gauss-Newton method and the Levenberg-Marquardt method, are often employed for parameter estimation in nonlinear models....

Purpose: Blood vessel networks within the retina are crucial for maintaining tissue perfusion and therefore good vision. Their complexity and unique patterns often require a steep learning curve for humans to identify trends and changes in the shape and topology of the networks, even though there exists much information important to identifying di...

Fitting models to data is critical in many science and engineering fields. A major task in fitting models to data is to estimate the value of each parameter in a given model. Iterative methods, such as the Gauss-Newton method and the Levenberg-Marquardt method, are often employed for parameter estimation in nonlinear models. However, practitioners...

Prior research has demonstrated how the average characteristics of a team impact team performance. Individual characteristics of team members and individual team member behavior have been largely ignored, especially in the context of engineering design. In this work, a behavioral study was conducted to uncover whether the most or least proficient m...

In order to computationally study design cognition under design process management, this work utilizes a topic modeling approach to analyze design team discourse during problem-solving. The particular experimental design, from previous work by the authors, places one of the design team conditions under the guidance of a human process manager. In th...

Through experience, designers develop guiding principles, or heuristics, to aid decision-making in familiar design domains. Generalized versions of common design heuristics have been identified across multiple domains and applied by novices to design problems. Previous work leveraged a sample of these common heuristics to assist in an agent-based d...

Products must often endure unpredictable and challenging conditions while fulfilling their intended functions. Game-theoretic methods make it possible for designers to design solutions that are robust against complicated conditions, however, these methods are often specific to the problems they investigate. This work introduces the Game-Augmented R...

After a child is born, the examination of the placenta by a pathologist for abnormalities such as infection or maternal vascular malperfusion can provide important information about the immediate and long-term health of the infant. Detection of the pathologic placental blood vessel lesion decidual vasculopathy (DV) has been shown to predict adverse...

Human-computer hybrid teams can meet challenges in designing complex engineered systems. However, the understanding of interaction in the hybrid teams is lacking. We review the literature and identify four key attributes to construct design research platforms that support multi-phase design, hybrid teams, multiple design scenarios, and data logging...

Human-computer hybrid teams can meet challenges in designing complex engineered systems. However, the understanding of interaction in the hybrid teams is lacking. We review the literature and identify four key attributes to construct design research platforms that support multi-phase design, hybrid teams, multiple design scenarios, and data logging...

Human designers often work in a visual design space, projecting step-by-step design progression through evolving mental images. The strategic evolution of that design leverages heuristics based on experience and domain knowledge. The methodology presented in this paper brings together the visual nature of design problem solving and design heuristic...

Design activity can be supported using inspirational stimuli (e.g., analogies, patents, etc.), by helping designers overcome impasses or in generating solutions with more positive characteristics during ideation. Design researchers typically generate inspirational stimuli a priori in order to investigate their impact. However, for a chosen stimulus...

Grammar-based design is typically a gradual process; incremental design changes are performed until a problem statement has been satisfied. While they offer an effective means for searching a design space, standard grammars risk being computationally costly because of the iteration required, and the larger a given grammar the broader the search req...

Design activity can be supported using inspirational stimuli (e.g., analogies, patents, etc.), by helping designers overcome impasses or in generating solutions with more positive characteristics during ideation. Design researchers typically generate inspirational stimuli a priori in order to investigate their impact. However, for a chosen stimulus...

Partnership between humans and computers has a significant potential to extend the ability of humans to address complex design problems. This paper presents a decision-making process for computers to effectively collaborate with humans in the solution of complex problems under dynamic competition. In the proposed process, the computers learn strate...

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design...

Machine learning is a powerful tool that can be applied to pattern search and mathematical optimization for making predictions on new data with unknown labels. In the field of medical imaging, one challenge with applying machine learning techniques is the limited size and relative expense of obtaining labeled data. For example, in glenoid labral te...

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design...

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design...

Solving any design problem involves planning and strategizing, where intermediate processes are identified and then sequenced. This is an abstract skill that designers learn over time and then use across similar problems. However, this transfer of strategies in design has not been effectively modeled or leveraged within computational agents. This n...

The ability to effectively analyse design concepts is essential for making early stage design decisions. Human evaluations, the most common assessment method, describe individual design concepts on a variety of ideation metrics. However, this approach falls short in creating a holistic representation of the design space as a whole that informs the...

Inspirational stimuli, such as analogies, are a prominent mechanism used to support designers. However, generating relevant inspirational stimuli remains challenging. This work explores the potential of using an untrained crowd workforce to generate stimuli for trained designers. Crowd workers developed solutions for twelve open-ended design proble...