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
[google_news title=”” keyword=”AI agents” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: AI agents
- Agents of manipulation (the real AI risk)on May 17, 2024 at 7:05 pm
Artificial agents will make our lives better. At the same time, these superpowers could easily be deployed as agents of manipulation.
- AI marketplace connects robot agents to pay humans to complete jobson May 16, 2024 at 9:29 pm
Payman is a marketplace that was created for AI robots to pay humans who can get do a job they can't. NBC News' Gadi Schwartz talks to Nita A. Farahany about the marketplace and the future of jobs in ...
- Protocol Village: FLock.io to Merge Decentralized AI Training With Morpheus 'Smart Agents'on May 16, 2024 at 3:03 pm
FLock.io, a platform for "AI co-creation," and Morpheus, a network for powering smart agents, announced a strategic partnership "to advance decentralized AI capabilities in Web3," according to the ...
- An AI agent may soon be at your beck and call, but it might cost you a bit of your privacyon May 15, 2024 at 5:52 am
The stakes for Google are high, as nailing AI agents opens up a massive business opportunity.
- Google takes on GPT-4o with Project Astra, an AI agent that understands dynamics of the worldon May 14, 2024 at 8:58 pm
Google says it plans to add some Project Astra capabilities to the Gemini mobile and web experiences later this year.
- Everything announced at Google I/O, including AI Agents, Ask Photos, and moreon May 14, 2024 at 12:16 pm
Google announced at I/O that Google Photos would get a powerful new AI tool called Ask Photos. Google said the feature can effectively parse through your pictures and answer questions you might have, ...
- Google strikes back at OpenAI with “Project Astra” AI agent prototypeon May 14, 2024 at 12:11 pm
Google also announced a new AI model called Gemini 1.5 Flash, which it billed as a lightweight, faster, and less expensive version of Gemini 1.5. "1.5 Flash is the newest addition to the Gemini model ...
- Google just gave us a tantalizing glimpse into the future of AI agentson May 14, 2024 at 10:51 am
Google is trying to turn AI chatbots into intelligent systems that can reason, plan, and remember. Project Astra is a window into this future.
- Google I/O 2024: 'AI Agents' are AI personal assistants that can return your shoeson May 14, 2024 at 10:51 am
Google will be sharing lots of products ready to utilize at today's big Google I/O event. However, one announcement from CEO Sundar Pichai was more of an idea that's in the works: AI Agents. According ...
- Retell AI lets companies build 'voice agents' to answer phone callson May 9, 2024 at 6:30 am
Call centers are embracing automation. According to research firm TechSci Research, the global market for contact center AI could grow to nearly $3 billion in 2028, from $2.4 billion in 2022.
via Bing News