I am training a bionic elephant’s trunk to do real-world jobs like picking apples or replacing light bulbs – something non-experts haven’t been able to do until now.
Designed to bring the dexterity of an elephant’s trunk to industrial robots, the appendage I am wrestling was launched by German engineering firm Festo.
[T]he machine wasn’t built with its own precision control software. Steil and his colleague Matthias Rolf used a process called “goal babbling” to mimic the way a baby learns to grab things by continually reaching – a process of trial and error that lets them work out which muscles they need to move.
Similarly, the robot remembers what happens to the trunk’s position when tiny changes are made to the pressure in the thin pneumatic tubes feeding the artificial muscles. This creates a map that relates the trunk’s precise position to the pressures in each tube.
In other words, you manually guide the robot-trunk to do what you want it to do, and it eventually learns how to call up that blueprint of muscle firings – essentially, exactly what a human child does.
Via New Scientist.