Now, robot that can `discover` new objects on its own
More than a good eye! Researchers, including an Indian-origin scientist, have developed a new `smart` robot that can analyse and learn about new objects on its own.
Washington: More than a good eye! Researchers, including an Indian-origin scientist, have developed a new `smart` robot that can analyse and learn about new objects on its own.
The two-armed mobile robot called HERB can `discover` more than 100 objects in a home-like laboratory, including items like computer monitors and plants.
Researchers at Carnegie Mellon University`s Robotics Institute built digital models and images of objects and loaded them into the memory of HERB - the Home-Exploring Robot Butler - so the robot could recognise objects that it needs to manipulate.
With the team`s implementation of HerbDisc, the robot could discover these objects on its own.
With more time and experience, HerbDisc gradually refines its models of the objects and begins to focus its attention on those that are most relevant to its goal - helping people accomplish tasks of daily living.
The robot`s ability to discover objects on its own sometimes takes even the researchers by surprise, said Siddhartha Srinivasa, associate professor of robotics and head of the Personal Robotics Lab, where HERB is being developed.
In one case, some students left the remains of lunch - a pineapple and a bag of bagels - in the lab when they went home for the evening.
The next morning, they returned to find that HERB had built digital models of both the pineapple and the bag and had figured out how it could pick up each one.
"We didn`t even know that these objects existed, but HERB did," said Srinivasa, who jointly supervised the research with Martial Hebert, professor of robotics.
"That was pretty fascinating," said Hebert.
Discovering and understanding objects in places filled with hundreds or thousands of things will be a crucial capability once robots begin working in the home and expanding their role in the workplace.
However, manually loading digital models of every object of possible relevance simply isn`t feasible, Srinivasa said.
Object recognition has long been a challenging area of enquiry for computer vision researchers. Recognising objects based on vision alone quickly becomes an intractable computational problem in a cluttered environment, Srinivasa said.