Robots to roam university to study ‘a socio-technical problem’

Will robots take over the world? Will our new machine leaders be generous gods or cruel taskmasters? A new research project isn’t going to answer these questions, but aims to highlight how people perceive and interact with some of our automatons in public.

Researchers at the University of Texas at Austin recently received expanded funding from the National Science Foundation to continue their work studying human-robot interactions. To do this, the team plans to release four-legged robots around campus and collect data on what they find. The project will start in 2023 and last five years.

“When we’re developing robots in the real world, it’s not just a technical problem, it’s actually a socio-technical problem,” Joydeep Biswas, an assistant professor of computer science in the College of Natural Sciences and a member of the research team, told Ars.

Big bot on campus

The team plans to use two varieties of “dog-like” robots made by Boston Dynamics and Unitree. The research team will network and members of the UT Austin community – students, staff, etc. The researchers plan to start with two robots, but Biswas said they will add more throughout the research.

While deployed, the robots will inevitably encounter (probably literally) pedestrians, cyclists, scooter riders and larger vehicles. Researchers will observe and study the interactions between these mobile humans and machines. The robots will be monitored either in person or remotely so researchers can collect data on how the robots interact with the humans they encounter and stop the robots if they act in undesirable ways. The team will also create a research database to collect the data from the study and explore how we can develop autonomous robots in human environments, “not just for five minutes or an hour, but for years at a time,” said Biswas.

Through the work, Biswas and his colleagues hope to learn how humans and robots interact, but also how robots can signal their intentions—how they can communicate the actions they’re about to take, particularly in complex situations where there are people, bikes. cars and scooters. In addition, the study will examine how robots learn to recover from their mistakes. For example, if a person loses his turn on a freeway, he does not immediately stop and make a U-turn. More work is needed on how robots can recover from errors safely, he said.

“This is a very difficult environment that we would like to be able to deal with,” Biswas said. “And I think the more unstructured environments these robots can handle without being disruptive while still being productive, the more progress we’re making.”

First steps

Biswa noted, however, that there are pros and cons to doing this study on a university campus. On the plus side, robots are more accessible to researchers, making their jobs easier. People in a university may also be a bit more used to or comfortable with robots than, say, people in an aged care facility. That’s a bit of a mixed blessing, but Biswas noted that a college campus is probably the best place to start.

“It’s an easier audience to work with … it might be a little more welcoming to these robots, and that’s actually probably a good thing to start with,” compared to, like, an old people’s home, he said.

Companies like Amazon and FedEx have recently canceled or scaled back their robotic delivery programs. According to Biswas, there could be many reasons for this, including financial considerations. But his and his colleagues’ upcoming research efforts are looking at the future of robotics, potentially several years down the road, “not the stuff today.”