One of the big challenges for the application of robots is their ability, or lack, to grip small, delicate, or irregular shaped objects. This challenge, however, is constantly being worked on, often by University research teams.
For example, in MIT’s Computer Science and Artificial Intelligence Laboratory, a soft robot hand, 3D-printed out of silicone rubber, has three fingers with special sensors that can estimate the size and shape of an object accurately enough to identify it from a set of multiple items. This allows the robot to compare new objects to ones it has previously picked up based on the similar data points. The robot is, therefore, able to pick up a variety of objects such as cups, eggs, CDs and tennis balls – all without damaging them. With this work, the researchers set out to develop both the soft hands and the supporting control and planning systems that make dynamic grasping possible.
Read more by Adam Conner-Simons, MIT CSAIL, 9/30/2015
A University of Washington team of computer scientists and engineers has built a robot hand that can not only perform dexterous manipulation but also learn from its own experience without needing humans to direct it. Hand manipulation is one of the hardest problems that roboticists have to solve.
This five-fingered robot hand can learn how to perform dexterous manipulation — like spinning a tube full of coffee beans — on its own, rather than having humans program its actions.
Read more by Jennifer Langston, UW Today, May 9, 2016