AI agents imitate engineers to construct effective new designs using visual cues like humans do
Trained AI agents can adopt human design strategies to solve problems, according to findings published in the ASME Journal of Mechanical Design.
Big design problems require creative and exploratory decision making, a skill in which humans excel. When engineers use artificial intelligence (AI), they have traditionally applied it to a problem within a defined set of rules rather than having it generally follow human strategies to create something new. This novel research 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 was co-authored by Jonathan Cagan, professor of mechanical engineering and interim dean of Carnegie Mellon University’s College of Engineering, Ayush Raina, a Ph.D. candidate in mechanical engineering at Carnegie Mellon, 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,” said Cagan. “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 focuses on truss problems because they represent complex engineering design challenges. 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 which 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,” said Raina.
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 (like making something lightweight) and did not receive feedback on how well they were doing. Instead, they only used the vision-based human strategy techniques they had been trained to use.
“It’s tempting to think that this AI will replace engineers, but that’s simply not true,” said McComb. “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.”
Learn more: AI learns to design
The Latest on: AI agents
via Google News
The Latest on: AI agents
- How AI is revolutionising the future of customer experienceon November 27, 2020 at 7:17 am
Artificial Intelligence or AI is the next frontier for enabling precise automation, digging deeper into data and accomplishing tasks with astonishing accuracy. With AI being applied to almost every ...
- Autonomous Agents Market 2020 Growth Factors, Top Manufacturers, Future Investment, Segmentation, Share, Size, CAGR, Latest Trends, Forecast 2025on November 26, 2020 at 10:43 am
Nov (The Expresswire) -- Global"Autonomous Agents Market"(2020-2026) status and position of worldwide and key regions, with perspectives ...
- ‘Superintelligence’ in Seattle: AI researchers do a reality check on a movie that adds romance to techon November 26, 2020 at 10:00 am
Seattle and the field of artificial intelligence get a share of the spotlight in HBO Max’s “Superintelligence” — but how much substance is behind the spotlight?
- Realtors, you should be using AI – here’s how (and how not to)on November 25, 2020 at 9:26 am
AI is changing the course of the real estate industry on a seismic scale. What does that mean for real estate pros?
- Tech Leaders Come Together to Build Out the Future of AI in Customer Supporton November 25, 2020 at 5:07 am
Forethought, an AI enterprise company, today unveiled its Customer Advisory Board. The group comprises industry leaders that advise on the future of AI in enterprise. Given each party's breadth of ...
- National Debt Relief Delivers Empathetic Customer Experiences By Leveraging Contact Center AI from Observe.AIon November 24, 2020 at 4:15 am
Observe.AI, a leader in Contact Center AI, today announced that its platform has enabled National Debt Relief (NDR) to improve customer experience, automate quality assurance, and provide better ...
- Global Autonomous Agents Market 2020 Growth Drivers, Regional Outlook, Competitive Strategies and Forecast up to 2026on November 24, 2020 at 2:15 am
Global Autonomous Agents Market 2020 by Company, Regions, Type and Application, Forecast to 2026 interprets market overview, value chain structure, industrial environment, regional analysis, ...
- Five9 Focuses On AI-based Contact Centerson November 23, 2020 at 6:00 am
I’m publishing this series to discuss a topic that I follow closely - cloud stocks, trends, strategy, acquisitions, and more. Please subscribe to my Cloud Stock Analysis series and never miss an ...
- To Teach an AI to Pursue Goals, Scientists Made It Play an RPGon November 21, 2020 at 7:47 am
In order to train AI to use language with intent, scientists from Facebook and the Georgia Institute of Technology dropped an algorithm into the middle of a roleplaying game, MIT Technology Review ...
- Fetch.AI launches blockchain-based AI smart-city infrastructure in Munichon November 20, 2020 at 3:41 am
Fetch.ai and Datarella predict mass implementation of Munich’s smart-city infrastructure will reduce CO2 emissions by 34,000 tonnes per year.
via Bing News