In an era of heightened fears about killer robots, teaching them martial arts may seem unwise. But researchers have now shown a robot how to flip nunchucks to demonstrate an intuitive approach for teaching complex manual tasks. The group built a bionic hand and a motion-capture glove that can be used to teach the robot by demonstration, a popular method for skills requiring dexterity. But that’s like learning from a silent teacher, the engineers say in research uploaded to the arXiv preprint server, so they devised an approach closer to how humans are taught. First, the teacher explains each step of the trick using an intuitive symbolic flow chart called a Petri net. Then, they demonstrate the trick and evaluate their own performance after every attempt, creating data the robot uses to learn the movements required at each step and develop criteria for self-evaluation as it practices. It took the robot a matter of hours to learn how to spin the nunchuck around the back of its hand and catch it again. But the approach is not task-specific, so the researchers say it could help teach all kinds of complex, dynamic motor skills now beyond robots, particularly those dealing with partly soft, partly rigid objects. That could include assembling car interiors or fruit picking. Or more advanced nunchuck tricks, of course.
Read our COVID-19 research and news.