A team of researchers from Carnegie Mellon University’s Human-Computer Interaction Institute (HCII) have demonstrated a new way to effectively increase learning and engagement for museum exhibits. The team relied on artificial intelligence (AI) to develop new interactive and hands-on exhibits, including an intelligent virtual assistant that interacts with visitors.
Compared to traditional exposure, the new smart exposure has been shown to increase learning and the time individuals spend at the exposure.
The team’s findings were published in the Journal of Learning Sciences.
Turning play into learning
Nesra Yannier is a member of the HCII faculty and responsible for the research project.
“Artificial intelligence and computer vision have turned play into learning,” Yannier said.
The team also included Ken Koedinger and Scott Hudson from CMU, Kevin Crowley from the University of Pittsburgh, and Youngwook Do from the Georgia Institute of Technology.
One of the popular exhibits in museums are earthquake exhibits, where children build towers and try to keep them from falling when the table shakes. There are often signs placed around the exhibit to engage children about science, but the evidence is unclear as to their effectiveness.
AI-enhanced earthquake table
Yannier led the team of researchers to build an AI-enhanced seismic table that had a camera, touchscreen, and large display. He also had NoRilla, which is an intelligent agent in the form of a virtual gorilla. NoRilla replaces traditional panels and interacts with participants by taking them through different challenges and asking questions regarding earthquake exhibits, such as why the towers did or did not fall.
The team tested smart earthquake displays at the Carnegie Science Center in Pittsburgh. Children attending summer camp at the center interacted with the smart or traditional exhibits, and they completed pre-tests and post-tests and surveys. The team also observed visitors as they interacted with the exhibit.
The surveys revealed that children learned a lot more from the smart display and had as much fun as the traditional display. The AI exhibit also helped children better understand science concepts and improve their building and engineering skills.
The study results also revealed that people spent around six minutes on the smart exposure, compared to 90 seconds on the traditional exposure.
Koedinger is a professor at the HCII.
“What’s particularly impressive to me is how the system engages kids in real science experiments and thinking,” Koedinger said. “The children not only understand, but also have more fun than the usual exhibitions, even if it takes more thinking.”
“Our exhibit has automated guidance and support that makes hands-on physical experimentation a valuable learning experience,” added Yannier. “In museums, parents may not have the knowledge to help their children, and staff may not always be available. Using AI and computer vision, we can bring this experience to more children from different backgrounds and on a larger scale. »
Yannier says this new technology could also help students in the classroom and at home, not just in a museum.