Researchers use machine learning to develop dexterous robotic hands

I’ve written previously on advances being made in the development of dexterous robotics that are being used in fields as diverse as oceanography and medicine.

Despite these advances, there is still much work to be done on creating more dexterous robotic digits that are capable of doing simple (to us) tasks such as rolling, bending and pivoting.

There are signs that progress is being made, with a team from the University of Washington developing a robot hand that can do many of these tasks without human direction.

“Hand manipulation is one of the hardest problems that roboticists have to solve,” the researchers say. “A lot of robots today have pretty capable arms but the hand is as simple as a suction cup or maybe a claw or a gripper.”

Read the full story by

Tags:

RELATED READS
Warning, reading this may alter your thinking FocusOn Learning Day 3, my Summary, and Leaving Austin

From our Network

6 Top EdTech Trends To Watch In 2017 

5 Ways To Jumpstart Your Restaurant’s Employee Training Program

6 Steps To Find Your Instructional Design Dream Job

6 Ways To Know If Your Learning Management System Is Worth The Investment

4 Tips To Infuse The Human Aspects Of Education Into eLearning