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
- Ajman Department of Ports and Customs Launches Artificial and Business Intelligence (AI/BI) Powered Serviceson January 9, 2020 at 6:41 am
launched in November 2018 an Integrated Customs System positioning the Emirate at the forefront of digital transformation in international trade and in conformity with the UAE Government's strategy ...
- Global Conversational AI Platforms Market Size was Valued at USD 2364 Million in 2018 and is Expected to grow at a CAGR of 26.75% | Valuates Reportson January 8, 2020 at 3:37 pm
/PRNewswire/ -- Increasing numbers of messaging apps and voice assistants drive the conversational AI platform market. Many companies invest in chatbots ...
- IEEE honors NYU Tandon Game Innovation Lab director for contributions to AIon January 8, 2020 at 12:53 pm
He is the co-author of the 2019 paper "Playing Atari with Six Neurons," which demonstrated that even simple AI systems can learn and which won the International Conference on Autonomous Agents and ...
- This AI Startup Is Improving Customer Call Experienceon January 8, 2020 at 5:14 am
He further added, “This random selection does not help in improving the overall quality of the call experience.” Observe.ai analyses 100 per cent of the calls leading to a better coaching and training ...
- AI in 2020: From Experimentation to Adoptionon January 7, 2020 at 11:15 am
Advances in data discovery and management, skills training and AI explainability are driving the rate of AI adoption faster than many predicted.
- New nevo.ai Features Extend Virtual Assistant Capabilities to Bring Intelligent Services, Virtual Agent, and Moreon January 7, 2020 at 9:10 am
Before it's here, it's on the Bloomberg Terminal.
- Announcing Allegro Trains Agent, Providing Effortless Cluster Management for Machine and Deep Learning Experimentson January 7, 2020 at 6:38 am
Allegro AI, the deep learning, computer vision open-source company, officially welcomes Allegro Trains Agent to the Allegro Trains ecosystem. Trains Agent is a complementary solution joining the ...
- The AI Eye: NICE inContact Partners with Zendesk and Arlo Launches SmartCloudon January 6, 2020 at 10:15 am
Point Roberts, WA and Vancouver, BC - January 6, 2020 (Investorideas.com Newswire) Investorideas.com (www.investorideas.com), a global investor news source covering Artificial Intelligence (AI) brings ...
- Seize the Opportunity to Differentiate with AI-Powered Digital Experienceson January 3, 2020 at 5:38 pm
Natural language processing can be also used to monitor a customer’s speech on a call in real-time, assess their emotional state, and flag them to a senior agent or supervisor if attention is required ...
- Using Meta-Learning to Train Agents to Learn Generic Conceptson December 31, 2019 at 7:13 am
Is it possible to recreate this neuroscientific miracle in artificial intelligence(AI) agents? Last year, researchers from OpenAI published a paper proposing a technique for concept learning based on ...
via Bing News