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
- Q&A: Three keys to scaling AI in insuranceon March 21, 2020 at 9:58 am
Artificial intelligence and machine learning are the newest comers to the insurtech landscape, set to transform the way that traditional insurance has been managed. Two innovators from Vertafore ...
- Statement Re WisdomTree Artificial Intelligence UCITS ETFon March 20, 2020 at 10:20 pm
If you are in any doubt about its content, please consult your stockbroker, bank manager, solicitor, accountant or other financial adviser. If you have sold or transferred all your shares in ...
- 4 Applications of AI in Customer Service That Work Todayon March 20, 2020 at 5:15 pm
But customer experience (CX) leaders know that AI-powered technologies can transform the way businesses understand core audiences. Customer service agents benefit from real-time and historical ...
- AI Isn't Replacing CX Professionals -- It's Making Them Betteron March 20, 2020 at 5:23 am
is getting a bad reputation. There’s a lot of buzz about emerging tech stealing the jobs of hardworking people -- especially those in the customer experience (CX) field. And while Forrester predicts ...
- How AI Solutions Are Solving 5 Long-Standing Business Challengeson March 20, 2020 at 5:20 am
Although every business is different, even those in completely separate industries face some of the same long-standing problems. In recent years, artificial intelligence has become the technology that ...
- Coronavirus is prompting companies to adopt AI call center solutionson March 19, 2020 at 7:30 am
“Businesses are looking for solutions that will allow them to solve customer problems while also ensuring the safety of their workforce through appropriate social distancing measures, and we are part ...
- Hybrid AI systems are quietly solving the problems of deep learningon March 19, 2020 at 3:54 am
Open-ended domains can be general-purpose chatbots and AI assistants, roads, homes, factories, stores, and many other settings where AI agents interact and cooperate directly with humans. As the past ...
- Artificial-intelligence-driven scanning probe microscopyon March 19, 2020 at 3:14 am
Enabling atomic-precision mapping and manipulation of surfaces, scanning probe microscopy requires constant human supervision to assess image quality and probe conditions. Here, the authors ...
- AI's role in transforming government call centerson March 18, 2020 at 6:12 pm
AI can act in several ways during a caller engagement to provide simpler and more natural, or frictionless, interactions that build confidence and trust. Its ability to act on natural-language voice ...
- AI Will Free Us From The Tyranny Of Monotonyon March 18, 2020 at 12:03 pm
How the power of machine learning is restoring humanity to customer service—and bringing joy to the way we work. What does the term “ghost in the machine” mean to you? Kudos to those of you who came ...
via Bing News