Robots loaded with newly developed software designed to help them deal efficiently with clutter have unexpectedly dealt with problems creatively in unanticipated ways.
Dealing with clutter is typically challenging for robots, while they are adept at ‘pick-and-place’ processes, picking up an object in a specified place and putting it down at another specified place, they struggle when items are disordered.
While this is not a problem for robots working on factory production lines for example, issues arise when they land on distant planets with rough landscapes for example or when navigating and cleaning people's homes.
A team from Carnegie Mellon University has developed new software helping robots cope with clutter, whether they're beating a path across the Moon or grabbing a milk jug from the back of the refrigerator.
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 and it can also be taught to pay attention to items that might be valuable or delicate.
While the software helped a test robot to deal more efficiently with clutter, it surprisingly revealed the robot's creativity in solving problems.
"It was exploiting sort of superhuman capabilities," Siddhartha Srinivasa, associate professor of robotics, said of his lab's two-armed mobile robot, the Home Exploring Robot Butler, or HERB.
"The robot's wrist has a 270-degree range, which led to behaviours we didn't expect. Sometimes, we're blinded by our own anthropomorphism."
In one case, the robot used the crook of its arm to cradle an object to be moved.
"We never taught it that," Srinivasa added.
When a person reaches for a milk carton in a refrigerator, they don’t typically move every other item out of the way. Instead they might move an item or two, while pushing others out of the way as the carton is pulled out.
The rearrangement planner automatically finds a balance between the two strategies, Srinivasa said, based on the robot's progress on its task
In addition to HERB, the 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.
One limitation of the system is that once the robot has evaluated a situation and developed a plan to move an object, it effectively closes its eyes to execute the plan.
Work is now underway to provide tactile and other feedback that can alert the robot to changes and miscalculations and can help it make corrections when necessary.
Another Carnegie Mellon team is also looking at ways to make robots interact more appropriately with their environment by giving them greater awareness.
Earlier this week, they demonstrated a robot with a camera attached to its hand that improved its spatial awareness by rapidly creating a 3-D model of its environment.