Indian-origin researchers develop new software to help robots with clutter

A new software that helps robots deal efficiently with clutter to accomplish their tasks, like grabbing a milk jug from the back of the refrigerator, has been developed by researchers, including one of Indian-origin. The software not only helped a robot deal efficiently with clutter, it also showed the robot’s creativity in solving problems, researchers said.

“It was exploiting sort of superhuman capabilities. The robot’s wrist has a 270-degree range, which led to behaviours we did not expect,” said Siddhartha Srinivasa from Carnegie Mellon University (CMU) in the US, while referring to his lab’s two-armed mobile called Home Exploring Robot Butler (HERB).

“Sometimes, we are blinded by our own anthropomorphism,” he said. In one case, the robot used the crook of its arm to cradle an object to be moved. “We never taught it that,” he said. In addition to HERB, the rearrangement planner software was tested on NASA’s KRex robot, which is being designed to traverse the lunar surface.

While HERB focused on clutter typical of a home, KRex used the software to find traversable paths across an obstacle-filled landscape while pushing an object.

Robots are adept at “pick-and-place” (P&P) processes, picking up an object in a specified place and putting it down at another specified place. Srinivasa said this has great applications in places where clutter is not a problem, such as factory production lines.

But that is not what robots encounter when they land on distant planets or, when “helpmate” robots eventually land in people’s homes, he said.

P&P simply does not scale up in a world full of clutter. When a person reaches for a milk carton in a refrigerator, he does not necessarily move every other item out of the way. Rather, a person might move an item or two, while shoving others out of the way as the carton is pulled out.

The rearrangement planner automatically finds a balance between the two strategies based on the robot’s progress on its task, researchers said. The robot is programmed to understand the basic physics of its world, so it has some idea of what can be pushed, lifted or stepped on, they said.

It can also be taught to pay attention to items that might be valuable or delicate, in case it must extricate a bull from a china shop, researchers said.