New Delhi, 2 June-2014, Agencies: Prime Minister Narendra Modi today hailed the formation of Telangana…
Many of the jobs humans would like robots to perform, such as packing items in warehouses, assisting bedridden patients or aiding soldiers on the front lines, aren’t yet possible because robots still don’t recognise and easily handle common objects.
People generally have no trouble folding socks or picking up water glasses because we’ve gone through “a big data collection process” called childhood, says Stefanie Tellex, a computer science professor at Brown University. For robots to do the same types of routine tasks, they also need access to reams of data on how to grasp and manipulate objects. Typically, this data comes from painstaking programming. But ideally, robots could get some information from each other.
That’s the theory behind Tellex’s “Million Object Challenge.” The goal is for robots around the world to learn how to spot and handle simple items from bowls to bananas, upload their data to the cloud and allow other robots to analyse and use the information.
Tellex’s lab in Rhode Island, has the air of a playful preschool. On the day I visit, a Baxter robot, an industrial machine produced by Rethink Robotics is scanning a small hairbrush. It moves its right arm back and forth above the object, measuring depth with an infrared sensor. Then, with its two-pronged gripper, it tries different grasps that might allow it to lift the brush. Once it has the object in the air, it shakes it to make sure the grip is secure.
Tellex and her graduate student John Oberlin have gathered — and are now sharing — data on roughly 200 items, starting with such things as a child’s shoe, a plastic boat, a rubber duck and cookware that originally belonged to her 3-year-old son. Other scientists can contribute their robots’ data, and Tellex hopes that together they will build a library of information on how robots should handle a million different items.
Projects like this are possible because many research robots use the same framework for programming, known as ROS. Once one machine learns a task, it can pass on the data to others — and those machines can upload feedback that will in turn refine the instructions given to subsequent machines. Tellex says the data about how to recognize and grasp any given object can be compressed to just five to 10 megabytes.
Tellex was a partner in a project called RoboBrain, which demonstrated how a robot could learn from another’s experience. Her collaborator Ashutosh Saxena, then at Cornell, taught his PR2 robot to lift cups and position them on a table. Then, at Brown, Tellex downloaded that information from the cloud and used it to train her Baxter to perform the same task.
As more researchers contribute to and refine cloud-based knowledge, Saxena, noew CEO of a startup called Brain of Things, says, “Robots should have access to all the information they need, at their fingertips.”— New York Times News Service