Washington, June 8 : Though robots moving around, doing household chores and fighting like humans is something limited to sci-fi films, scientists are trying hard to build androids that simulate humans in many activities. And they have taken a major step in this direction by creating a mobile robotic arm with the ability to "see" its environment through a digital camera.
Developed by Dov Katz and Oliver Brock, a professor of computer science, at the University of Massachusetts Amherst, this robotic arm will see robots proving beneficial in many areas including medical care, household assistance and planetary exploration.
"Mobile robots play an important role in many settings, including planetary exploration and manufacturing. Giving them the ability to manipulate objects will extend their use in medical care and household assistance," said Katz, a doctoral student of computer science.
Till date, this robot, dubbed the UMan, or UMass Mobile Manipulator, has been taught to approach unfamiliar objects, such as scissors, garden shears and jointed wooden toys - and learn how they work by pushing on them and observing how they change, the same process used by children as they explore the world.
Just like a child, the Uman also stores this knowledge of how the objects move as a "kinematic model" which can be used to perform specific tasks, such as opening scissors and shears to a 90 degree angle. In fact, one video shot by the team shows UMan easily completing this task. In fact, Katz said that the easy part was to teach the UMan, how to "walk." "UMan sits on a base with four wheels that allow it to move in any direction, and a system of lasers keeps it from bumping into objects by judging their distance from the base," said Katz, who filmed the UMan taking its first trip around the laboratory navigating through a maze of boxes.
However, it was more difficult to teach the robotic arm to manipulate objects.
"Robots in factories perform complex tasks with ease, but one screw out of place can shut down the entire assembly line. Giving robots the same skills as humans turned out to be much more difficult than we imagined, which is why we don't have robots working in unstructured environments like homes," said Katz, who recently met with representatives from Toyota Motors.
And the most important part was to give the UMan eyes in the form of a digital camera that sits on the wrist. After adding the camera, which coupled manipulating objects with the ability to "see," the complex computer algorithms needed to instruct the UMan to perform specific tasks became much simpler.
In a video, the team shows what the UMan "sees" as it approaches a jointed wooden toy on a wooden table, which appears as a uniform field of green dots. The first gentle touch from the hand quickly separates the toy from the background, and moving the various parts eventually labels each section with a specific color, identifying all the moving pieces and the joints holding them together. UMan then stores this knowledge, and can use it to put the object in a specific shape.
Katz and Brock are planning further research to teach UMan to operate different types of machines, including doorknobs and light switches, and work on taking UMan's manipulation skills into three dimensions.
"Once robots learn to combine movement, perception and the manipulation of objects, they will be able to perform meaningful work in environments that are unstructured and constantly changing. At that point, we will have robots that can explore new planets and clean houses in a flexible way," said Katz.
The results of the study were presented at the Proceedings of the International Electrical and Electronics Engineers Conference on Robotics and Automation in Pasadena, Calif.