Robots have already become an indispensable part of our lives. However currently, most robots are relatively rigid machines which make unnatural movements. In contrast, humans seem to be able to manipulate objects with our fingers with incredible ease like sifting through a bunch of keys in the dark, tossing and catching a cube, tying a knot, insert a pin in a hole or use a hand tool such as a drill. But these are really very complex and involve extremely fine finger and hand motions.
For decades, roboticists have been trying to understand and imitate dexterous human manipulation. And while there has been much progress in machine perception, dexterous manipulation remained elusive.
The fine motor skill (or dexterity) achieved in humans is through the coordination of small muscles, in movements—usually involving the synchronization of hands and fingers—with the eyes. The complex levels of manual dexterity that humans exhibit can be attributed to and demonstrated in tasks controlled by the nervous system.
Examples of autonomous, robotic dexterous manipulation are still confined to the research laboratory. At present, autonomous, real time dexterous manipulation in unknown environments still eludes us. In spite of the enormous challenge, autonomous robots are poised to make huge leaps in their ability to manipulate unfamiliar objects. Recent advances in machine learning, Big Data, and robot perception have put us on the threshold of a quantum leap in the ability of robots to perform fine motor tasks and function in uncontrolled environments, says Robert Platt, computer science professor.
Some companies, such as KUKA, have already developed a dexterous robot arm with sensors in every joint. This solution might be more expensive, but it still enables the feasibility of dexterous manipulation.
In 2018, the Berkley OpenAI group demonstrated that this hurdle may finally succumb to machine learning as well. Given 200 years worth of practice, machines learned to manipulate a physical object with amazing fluidity. This might be the beginning of a new age for dexterous robotics.”
Defense Advanced Research Projects Agency (DARPA), an agency under the U.S. Department of Defense, has been working to improve the quality of robots. It is now conducting a global competition to design robots that can perform dangerous rescue work after nuclear accidents, earthquakes and tsunamis.
The robots are tested for their ability to open doors, turn valves, connect hoses, use hand tools to cut panels, drive vehicles, clear debris and climb a stair ladder — all tasks that are relatively simple for humans, but very difficult for robots.
IDST Monthly Access Membership Required
You must be a IDST Monthly Access member to access this content.