According to data from the International Federation of Robotics, an industry group, sales of workplace robots worldwide are steadily growing after a recent slowdown in growth caused by the pandemic. Sales of ‘collaborative robots’, i.e. robots that work in the same physical space as humans without necessarily helping them directly, grew by 6 percent globally in 2020, compared to 0.5 percent for all industrial robots in the same period.
Last week, Amazon unveiled a new mobile robot called Proteus, which has its own rudimentary ability to sense people. While other robots at Amazon facilities work in physical spaces separate from humans, such as moving shelves of goods within reach of human workers, Proteus can navigate areas where humans are working. It uses sensors to look out for people or other obstacles and stops when it detects it bumping into someone. Amazon’s announcement “indicates that they are investing in an ever-expanding partnership,” said Brad Porter, who previously served as vice president of robotics at Amazon and is now the founder and CEO of Collaborative Robots, another startup working on robots that are designed to work. closer to humans.
Robust AI hopes to move beyond Amazon by developing robots that can see what human workers are doing and help them do it. Brooks says this should make human labor less repetitive and could help employees take on new responsibilities. “We’re not trying to replace people here,” he says. “We want to make robots work for people, not the other way around.”
Clara Vu, co-founder and CTO of Veo Robotics, a company that has developed software that allows even large, powerful robots to be used safely, says the possibilities for teamwork between humans and robots are increasing as the technology needed to detect is mapped. to bring and move through human workplaces is becoming more common. “We’re finding more and more robots and people working together,” she says. “People are starting to see the capabilities of humans and robots as really complementary.”
Robust AI is targeting its technology at smaller warehouses that don’t currently use much automation. Matt Beane, an assistant professor at UC Santa Barbara who studies how organizations use AI and robotics, and who has consulted for Robust AI, says many companies are unable to completely redesign their operations around conventional automation that doesn’t work well with humans. . Companies in that position are more likely to invest in something like Carter, he says, but it can be tricky to measure the return an operation gets from this kind of human-robot teamwork.
Bilge Mutlu, a professor at the University of Wisconsin-Madison, has conducted research showing that human-robot collaboration can sometimes improve productivity. He has done work with Boeing where robots have robots perform a procedure such as applying coatings or sanding to make aircraft parts while a human supervises the work, intervening only when necessary. But Mutlu says collaboration doesn’t always improve things and it’s not always clear how best to implement that. “In academia, we’re making these impressive demos and stuff, but the science isn’t quite there yet,” he says.
Brooks’ latest robot is already making for a great demo, but it will need to help more companies make the leap to automation to succeed.
This post This warehouse robot reads human body language to become a better colleague
was original published at “https://www.wired.com/story/warehouse-robot-reads-body-language/”