We will be hosting the Frontiers in Design Representation Summer School 2022 at UMD from July 25-29, 2022 in College Park, MD. See the main Summer School website for more information and details on how to apply: https://ideal.umd.edu/FinDeR/

Mark recently had to give a pre-recorded invited talk as part of a conference. We uploaded the video to YouTube in case others wanted to watch as well. Video is 18 minutes long and covers much of the work covered in Wei Chen’s dissertation, including the following papers:

• http://ideal.umd.edu/papers/paper/aiaaj-beziergan
• http://ideal.umd.edu/papers/paper/jmd-hgan
• http://ideal.umd.edu/papers/paper/scitech-airfoil-opt
• http://ideal.umd.edu/papers/paper/arxiv-bezier-gan
• http://ideal.umd.edu/papers/paper/samo-aes
• http://ideal.umd.edu/papers/paper/jmd-feasible-designs
• http://ideal.umd.edu/papers/paper/jmd-design-manifolds

Our article entitled “Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks” was accepted for publication in the AIAA Journal. Check out the publications page for more information.

Dr. Mark Fuge has received an NSF CAREER award to study new Machine Learning algorithms with the goal of enabling computers that learn how to design complex systems like new aircraft or vehicles. See the College of Engineering News Story for more details: https://enme.umd.edu/news/story/fuge-receives-nsf-career-award

Our article entitled “Synthesizing Designs with Inter-Part Dependencies using Hierarchical Generative Adversarial Networks” was accepted for publication in the ASME Journal of Mechanical Design. Check out the publications page for more information.

Our article entitled “Checking the Automated Construction of Finite Element Simulations from Dirichlet Boundary Conditions” was accepted to this year’s IDETC. Check out the publications page for more information.

Our article entitled “Unpacking Subjective Creativity Ratings: Using Embeddings to Explain and Measure Idea Novelty” was accepted to this year’s IDETC. Check out the publications page for more information.

Our article entitled “Synthesizing Designs with Inter-part Dependencies Using Hierarchical Generative Adversarial Networks” was accepted to this year’s IDETC. We will be presenting this paper at the 44th Design Automation Conference. Check out the publications page for more information.

Citrine Informatics featured our new Pre-Print “Applying machine learning techniques to predict the properties of energetic materials” in the “New Literature Worth Reading” section of its Data-Driven Material Science and Chemistry Newsletter!

Our article entitled “Active expansion sampling for learning feasible domains in an unbounded input space” was published in Structural and Multidisciplinary Optimization (SAMO). Check out the publications page for more information.

Mark was recently a guest on the IBM Business of Government hour, where he discussed the IDEAL lab’s work, the future of Data-Driven Design, and some of the challenges it faces. You can listen to the podcast here.

Dr. Mark Fuge is leading a UMD team recently awarded a project as part of the DARPA Fundamentals of Design (FUN DESIGN) program for a project entitled “Learning to Move: From Operads to Fields to Functioning Topologies”. The project explores how techniques from Category Theory, Reinforcement Learning, and Functional Programming can fundamentally re-think and automatically re-discover how conceptual design of mechanical systems works.

Multiple postdoctoral positions are open in our lab to study fundamental mathematical and computational techniques for the conceptual design of engineered systems. Specifically, we are looking for talented researchers with expertise and a publication track-record in one (or more) of the following areas:

• Design Theory and Methodology, for example, in Computational Design Synthesis for engineering systems involving the interplay of function, behavior, and structure.
• Data-Driven Design and Optimization, for example, simulation-based design, multi-fidelity optimization, robotics, or optimal control.
• Computer Science, for example, machine learning/AI, software architecture, functional programming, lambda-calculus, and computer graphics/geometry.
• Applied Mathematics, for example, operator algebras, category theory, differential geometry, topology, or mathematical logic.

For more information, see the official posting

Dr. Mark Fuge has been awarded a DARPA Young Faculty Award for a project entitled “Topology and Synthesis of Design Manifolds” as part of the “Functional Mathematical Tools for Design” topic area. The grant builds upon our past work in Design Manifolds by studying how multiple part manifolds interact in assemblies and how mathematical tools from topology, group theory, and machine learning can aid human exploration of large, complex design spaces.

Faez has been selected for HCOMP Doctoral Consortium to be held in Quebec City, Canada on October 23, 2017. The consortium provides a unique opportunity to meet other students and experienced researchers in the field.

Our article entitled “Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space” is available on arXiv. Check out the publications page for more information.

Dr. Mark Fuge has been awarded an National Science Foundation grant from the CMMI Engineering Systems and Design program for a project entitled “Collaborative Research: Improving the Validity and Reliability of Creativity Ratings in Engineering Design” in partnership with Scarlett Miller and Sam Hunter from Penn State University. The grant builds upon our past work in creativity measurement and statistics by studying how to verify and validate different measurement scales for how to systematically measure creativity.

Faez has been granted IJCAI Student Grant to present his paper in Melbourne, Australia on August 23, 2017.

Mark will be giving a talk entitled “Designing with Data: How machine learning is morphing human, product, and system design” at the Machine Learning for Materials Research Workshop on June, 30th. Come check it out.

Our article entitled “Beyond the Known: Detecting Novel Feasible Domains over an Unbounded Design Space” was accepted for publication in the ASME Journal of Mechanical Design. Check out the publications page for more information.

Dr. Mark Fuge has been awarded the Gemstone Mentor of the Year Award for his work with UMD’s Gemstone program an undergraduate research program.

Faez has been selected for Kulkarni Summer Research Fellowship at University of Maryland, College Park.

Dr. Mark Fuge and Dr. Peter Chung in partnership with ETC have been awarded a grant from the Office of Naval Research for a project entitled “Machine Learning for Energetic Materials”. The grant studies how to use tools from machine learning to understand new material compositions through both materials databases and academic literature (such as, journal papers).

Our article entitled “Design Manifolds Capture the Intrinsic Complexity and Dimension of Design Spaces” was accepted for publication in the ASME Journal of Mechanical Design. Check out the publications page for more information.

Team PRINT, an Undergraduate Gemstone research team advised by Dr. Mark Fuge, has been awarded a Mindlin Foundation grant for a project entitled “Stroke-based Symbolic Vocabulary Implementation in Computer Aided Design”. The project studies how non-experts use symbols and gestures to identify common CAD operations with the goal of improving sketch-based CAD interfaces.

We’ll be presenting a paper at this year’s IDETC in the 42nd Design Automation Conference. The paper, entitled “How Designs Differ: Non-Linear Embeddings Illuminate Intrinsic Design Complexity”, shows how to measure the complexity and reduce the dimensionality of a geometric design space. Check out the paper on our publications page.

Our PhD students, Wei and Faez, have passed their qualifying exams. Congrats to them!

Our article entitled “The MechProcessor: Helping Novices Design Printable Mechanisms across Different Printers” was accepted for publication in the ASME Journal of Mechanical Design. Check out the project page for more updates when we release the source code for the paper.

We’ll be presenting a paper at this year’s IDETC in the Design Theory and Methodology (DTM) track: DTM-7 Human Behavior in Design. The paper, entitled “A Scalpel not a Sword: On the Role of Statistical Tests in Design Cognition”, explores how researchers in DTM use Null Hypothesis Statistical Testing in Design studies, and reviews some of the pitfalls associated with the practice. Check out the paper on our publications page. We’re looking forward to seeing everyone in Boston in August!

For those interested in Human-Centered Design, Design for Development, or statistical techniques for analyzing design research: keep a look out for our recently accepted paper on the Pattern Analysis Techniques for HCD Methods in the upcoming JMD special issue on “User Needs and Preferences in Engineering Design”. Also check out the HCD project page for more details and the project code.

IDEAL member Ryan Elder receives a UMD SEEDS Fellowship, funded through the National Science Foundation, for our work on 3D Printable Devices.

Mark will be giving a talk on Collaborative Design Informatics at Accenture Tech Labs on July, 22nd. Come check it out.

Our article on “Machine Learning Methods for Recommending Design Methods” was accepted for publication in the ASME Journal of Mechanical Design. Check out the project page for more updates when we release the source code for the paper.

We’ll be presenting two papers at this year’s IDETC, both in the Design Theory and Methodology (DTM) track. One paper is on the evolution of the OpenIDEO design community, and another is on users research methods for Design for Development. Check out the papers on our publications page. We’re looking forward to seeing everyone in Buffalo in August.

Mark will be giving a talk on Collaborative Design Informatics at GE Global Research in San Ramon. They’re doing some impressive work at the intersection of engineering and data science, building out the future of the industrial internet.

For those interested in Open Innovation or distributed design communities: keep a look out for our recently accepted paper on the Network Structure of OpenIDEO in one of the upcoming editions of JCISE.