AI Learns to Design
By Marika YangMedia Inquiries
- College of Engineering
Big design problems require creative and exploratory decision making, a skill in which humans excel. When engineers use artificial intelligence (AI), they traditionally have applied it to a problem within a defined set of rules rather than having it generally follow human strategies to create something new.
Novel research by Carnegie Mellon University considers an AI framework that learns human design strategies through observation of human data to generate new designs without explicit goal information, bias or guidance.
The study published in the ASME Journal of Mechanical Design was co-authored by Jonathan Cagan, professor of mechanical engineering and interim dean of the College of Engineering; Ayush Raina, a Ph.D. candidate in mechanical engineering at CMU; and Chris McComb, an assistant professor of engineering design at the Pennsylvania State University.
"The AI is not just mimicking or regurgitating solutions that already exist," Cagan said. "It’s learning how people solve a specific type of problem and creating new design solutions from scratch." How good can AI be? "The answer is quite good."
The study focused on truss problems. Commonly seen in bridges, a truss is an assembly of rods forming a complete structure. The AI agents were trained to observe the progression in design modification sequences that had been followed in creating a truss based on the same visual information that engineers use — pixels on a screen — but without further context. When it was the agents’ turn to design, they imagined design progressions that were similar to those used by humans and then generated design moves to realize them. The researchers emphasized visualization in the process because vision is an integral part of how humans perceive the world and go about solving problems.
The framework was made up of multiple deep neural networks that worked together in a prediction-based situation. Using a neural network, the AI looked through a set of five sequential images and predicted the next design using the information it gathered from these images.
"We were trying to have the agents create designs similar to how humans do it, imitating the process they use: how they look at the design, how they take the next action, and then create a new design, step by step," Raina said.
The researchers tested the AI agents on similar problems and found that on average, they performed better than humans. Yet, this success came without many of the advantages humans have available when they are solving problems. Unlike humans, the agents were not working with a specific goal, such as making something lightweight, and did not receive feedback on how well they were doing. Instead, they only used the vision-based human strategy techniques for which they had been trained.
"It’s tempting to think that this AI will replace engineers, but that’s simply not true," McComb said. "Instead, it can fundamentally change how engineers work. If we can offload boring, time-consuming tasks to an AI, like we did in the work, then we free engineers up to think big and solve problems creatively."
This paper is part of a larger research project sponsored by the Defense Advanced Research Projects Agency (DARPA) about the role of AI in human/computer hybrid teams, specifically how humans and AI can work together. With the results from this project, the researchers are considering how AI could be used as a partner or guide to improve human processes to achieve results that are better than humans or AI on their own.
Carnegie Mellon University is committed to educating, empowering and aligning its community around the world to address the Sustainable Development Goals, also known as the Global Goals, which aim to create a more peaceful, prosperous planet with just and inclusive societies. Recognizing the critical contributions that universities are making through education, research and practice, CMU publicly committed to undertaking a Voluntary University Review of the Global Goals. The 17 Global Goals cover wide-ranging issues, including reducing violence, ending extreme poverty, promoting equitable education, fighting inequality and injustice, advancing economic growth and decent work, and preventing the harmful effects of climate change by 2030.
The preceding story demonstrates CMU's work toward attaining Global Goal 9.