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
- Serviceaide Releases Industry First Knowledge-Centered Virtual Agenton October 6, 2020 at 10:37 pm
Centered Virtual Agent By CIOReview - Luma addresses these challenges using AI technologies like natural language processing and machine learning to serve up ...
- How conversational AI is shaping the future of bankingon October 6, 2020 at 10:26 pm
Adapt to customer needs Conversational artificial intelligence (AI) is the backbone of digital employees, which differ from chatbots in a number of ways, starting with their ability to handle customer ...
- AI researchers challenge a robot to ride a skateboard in simulationon October 6, 2020 at 8:46 am
Nvidia AI researchers say they've created a framework for controlling four-legged robots that promises better energy efficiency and adaptability.
- Kore.ai Eyes Major Growth for Conversational AI in Asia-Pacific; Opens Office in Japanon October 6, 2020 at 4:30 am
ORLANDO, FL and TOKYO, JAPAN / ACCESSWIRE / October 6, 2020 / Kore.ai, a market-leading Enterprise Conversational AI/Digital App Technology Platform and Virtual Assistant Solutions company, has ...
- UMaine researchers are developing AI to identify birds in aerial photoson October 5, 2020 at 12:31 pm
The project recently received $43,000 from the UMaine AI Initiative seed grant funding program, and builds on previous grants and partnerships involving UMaine faculty and state and federal agency ...
- neXt Posts AI-Created Trailer Expected to Haunt Our Dreams for Dayson October 5, 2020 at 11:02 am
With FOX's tech thriller/mystery neXt premiering this week, check out this AI-created trailer we're sure will haunt our dreams for days.
- CINC Goes All In on Lead Engagement and Conversion with the Introduction of CINC AIon October 5, 2020 at 9:00 am
CINC ( the number one lead generation and conversion platform for elite agents and teams, today announced the release of the industry’s most innovative communication tool: CINC AI. Built with ...
- Why AI can’t ever reach its full potential without a physical bodyon October 5, 2020 at 6:40 am
It would seem that there are no areas that are beyond improvement by AI – no tasks that cannot be automated, no problems that can’t at least be helped by an AI application. But is this strictly true?
- 4 Ways That AI Is Improving the Customer Experienceon October 5, 2020 at 6:22 am
As one of the leading trends in technology, Artificial Intelligence (AI) continues to gain in popularity for marketers and sales professionals, and has grown to be an essential tool for brands that ...
- Cloud AI Can Help You Survive The Stormon October 5, 2020 at 4:24 am
As you work to better understand and take action to improve user experiences and drive business outcomes, take care in your implementation and the use cases to which you apply AI.
via Bing News