Google reveals more robot development research
Google, which recently filed a patent for a driverless parcel delivery vehicle and released videos of a parcel-handling robot, has now reported that “great strides” have been made in developing robotic motor skills. In an article posted on Google’s Research Blog yesterday (8 March), Google Research Scientist Sergey Levine commented: “Machines still have a very long way to go to match human proficiency even at basic sensorimotor skills like grasping. However, by linking learning with continuous feedback and control, we might begin to bridge that gap, and in so doing make it possible for robots to intelligently and reliably handle the complexities of the real world.”
The Google Research team has been running a project using a network of 14 robots, which continually attempted a series of tasks designed to build up their ability to grasp, handle and sort objects.
“Observing the behaviour of the robot after over 800,000 grasp attempts, which is equivalent to about 3000 robot-hours of practice, we can see the beginnings of intelligent reactive behaviours,” said Levine.
“The robot observes its own gripper and corrects its motions in real time. It also exhibits interesting pre-grasp behaviors, like isolating a single object from a group. All of these behaviors emerged naturally from learning, rather than being programmed into the system.”
Levine’s article features a number of videos showing the robots picking and sorting objects – and the applicability to industrial sortation tasks is fairly obvious. Google’s automated/robotic systems for packing, sorting and delivering post and parcels are clearly not “market-ready” yet – but they do offer an interesting glimpse of what might be in store.
