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
- Omnichannel AI Virtual Agents, a COVID-19 antidote?on June 4, 2020 at 8:31 pm
COVID-19 has created a perfect storm for the call center industry. Many companies are grappling with unprecedented call volume as a result of disruptions to their core business while, at the same time ...
- Agents of SHIELD Season 7: The Koenig Family Mysteryon June 4, 2020 at 5:16 pm
The origins of the lookalike Koenig family have been an Agents of SHIELD mystery from the start. Are answers forthcoming in season 7?
- A top Amazon AI exec shares the 4 steps the e-commerce giant took to become a leader in adopting the advanced techon June 4, 2020 at 6:05 am
Swami Sivasubramanian stressed championing the ideal culture, understanding data needs, team-building, and finding the "right" problem.
- Neptune Flood Launches First All-Digital, AI-Driven Commercial Flood Insurance Product for Small and Medium Sized Businesseson June 4, 2020 at 4:00 am
PRNewswire/ -- Neptune Flood, the first all-digital, AI-driven, flood insurance company announced today that it now offers commercial flood insurance in ...
- CX During a Pandemic: 3 Ways to Empower Agents and Meet Your Customers Where They Areon June 3, 2020 at 11:40 am
Customers are increasingly turning to the fast and convenient channels that they typically use to interact with friends and family – like WhatsApp, chat, and social media messaging – to interact with ...
- Xeo AI & China Telecom (Americas) Team up to Advance Canadian Enterprises' Global Communicationson June 3, 2020 at 7:14 am
PRNewswire-PRWeb/ -- Xeo AI, the fast-growing Canadian Technology Distributor for information, communications and ...
- Intelligent Virtual Agent Product and Market Report (2020 to 2021) - IVAs Have a Critical Role in the COVID-19 Crisis - ResearchAndMarkets.comon June 3, 2020 at 6:19 am
Intelligent Virtual Agent Product and Market Report" has been added to ResearchAndMarkets.com's offering. The critical role of IVAs on the front line of self-service during the COVID-19 crisis has ...
- How Forward-Thinking CFOs Are Leading The AI Chargeon June 2, 2020 at 6:32 am
Forward-looking CFOs manage not only the bottom line but also the top line. They care about growing market share, revenue and the long-term financial health of the business, as well as competitive ...
- How Artificial Intelligence Can Lighten The Load For Customer Service Representativeson June 2, 2020 at 4:28 am
The simple truth is that an AI colleague is, in many ways, better equipped to be a customer service agent, and that is a good thing for people.
- Samoan AI-based Virtual Agent Piloted To Ease Public Consultation Barrierson June 1, 2020 at 9:55 pm
An AI powered agent named Tala may open the door on a new way of measuring sentiment and getting feedback from New Zealand’s ethnic communities. Developed and designed by Beca, one of Asia Pacific’s ...
via Bing News