Will robots take over the world? Will our new machine masters be gracious gods or cruel mission bosses? a New research project It won’t answer these questions, but it aims to shed light on how humans perceive and interact with some of our automated machines in public.
Researchers at the University of Texas at Austin recently received expanded funding from National Science Foundation To continue their work in the study of human-robot interactions. To do this, the team plans to launch four-legged robots around the campus and collect data on what it finds. The project will start in 2023 and run for five years.
“When we deploy robotics in the real world, it’s not just a technical problem, it’s actually a social and technical problem,” Joydeep Biswas, assistant professor of computer science in the College of Natural Sciences and a member of the research team, told Ars.
Big robot on campus
The team plans to use two types of “dog-like” robots made by Boston Dynamics and Unitree. The research team will create a network, and members of the UT Austin community — students, staff, etc. — will be able to use an app on their smartphone to deliver items like hand wipes and sanitizer. The researchers plan to start with two robots, but Biswas said they will add more during the research.
As they are deployed, the robots will inevitably (possibly literally) hit pedestrians, cyclists, motorcyclists, and larger vehicles. Researchers will monitor and study the interactions between these humans and mobile machines. The bots will be monitored either in person or remotely so that researchers can collect data on how the bots interact with the humans they encounter and stop the bots if they behave in undesirable ways. The team will also create a research database to collect data from the study and investigate how autonomous robots deploy in human environments, “not just for five minutes or an hour, but for years at a time,” Biswas said.
Through the work, Biswas and his colleagues hope to learn about how humans and robots interact, but also how robots can signal their intentions — how they can communicate actions they are about to take, particularly in complex situations where there are humans and bicycles, cars and motorcycles. In addition, the study will look at how robots learn to recover from their mistakes. For example, if a human misses his turn on a highway, he will not stop immediately and pull a turn. He said more work is needed on how to safely recover bots from bugs.
“This is kind of a really difficult setup that we would like to be able to tackle,” Biswas said. “And I think the more unstructured environments these robots can handle with strength and precision without being a nuisance, while still being productive, the more progress we can make.”
Biswas noted, however, that there are pros and cons to conducting this study on campus. On the plus side, researchers have access to robots, which makes their jobs easier. People at university may also be more familiar with or comfortable around robots than people in a nursing home, for example. This is somewhat of a mixed blessing, but Biswas noted that the campus is perhaps a better place to start.
“It’s an easier audience to work with,” he said. “They might be a little more welcoming to these bots, which is actually probably a good idea to start with,” compared to, like, the home of an old folk.
Owns companies like Amazon and FedEx recently ruled out or minimizing their automated delivery programs. According to Biswas, there can be many reasons for this, including economic ones. But his and his colleagues’ upcoming research efforts are looking into the future of robotics, perhaps several years later, “not the things of today.”
#Robots #roam #university #study #technological #social #problem