We use Machine Learning, Artificial Intelligence, and Crowdsourcing to understand how **large groups of people** design things and how **complex engineered systems** work, so that we can use the data they produce to make them better.

Some of the fundamental scientific questions we study include: What are efficient and useful ways to **computationally and mathematically represent designs**? How do we **combine physics-driven and data-driven models** to design better products? What makes **design collaboration** between large groups of people work well or poorly? How can we use tools from **applied mathematics** (such as graph theory, category theory, and statistics) and **computer science** (such as complexity theory, submodular optimization, and artificial intelligence) to better **understand how humans design?**

Some past practical applications of our research include: a fully automated system for inferring what makes designs creative given human feedback; the world’s first polynomial time algorithm for diverse bi-partite b-matching; algorithms for exploring and optimizing high-dimensional design spaces (e.g., aircraft); software for helping novices 3D print working mechanical devices; and network analyses of online collaborative design networks such as OpenIDEO.

You can read more about our work by looking at our **papers** or by reproducing any of our **open-source code**.

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.

Posted
14 Dec 2017
by Mark

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.

Posted
06 Nov 2017
by Mark

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

Posted
06 Oct 2017
by Mark

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.

Posted
30 Aug 2017
by Mark

Creative Exploration Using Topic Based Bisociative Networks

Faez Ahmed and Mark Fuge *Design Science* 2018

Published
05 Jan 2018

Published
01 Sep 2017

Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space

Wei Chen and Mark Fuge *arXiv* 2017

Published
29 Aug 2017

Published
23 Aug 2017

Beyond the Known: Detecting Novel Feasible Domains over an Unbounded Design Space

Wei Chen and Mark Fuge *JMD* 2017

Published
16 Jun 2017