Stanford University has launched an update to its JackRabbot campus robot, with the additions of a face and an arm to help people around the university grounds.
The original JackRabbot was developed to navigate around the campus with sensors built into its face, building up a map of its surroundings and avoiding obstacles including pedestrians and objects.
Like its predecessor, JackRabbot 2 features the same sensors, but ups the ante with it able to converse with humans and use its arm to deliver goods, take items out of the fridge and cleaning up after students.
“The JackRabbot project is developing a robot that doesn’t just navigate an environment by following the behavior of a traditional robotic system, such as going from Point A to Point B and avoiding bumping into obstacles,” Silvio Savarese, associate professor of computer science said.
“We want a robot that is also aware of the surroundings and the social aspects of human-robotics interactions, so it can move among humans in a more natural way.”
The researchers are now testing the more advanced features of JackRabbot, including compiling the vast swathes of data needed to power the algorithm that allows JackRabbot 2 to be socially aware. The researchers think JackRabbot will need at least 24 hours of data to make it work just like a human.
“There are many behaviors that we humans subconsciously follow – when I’m walking through crowds, I maintain personal distance or, if I’m talking with you, someone wouldn’t go between us and interrupt,” Ashwini Pokle, a graduate student in the Stanford Vision and Learning Lab added. “We’re working on these deep learning algorithms so that the robot can adapt these behaviors and be more polite to people.”
