The goal of this work was to enable trans-radial amputees to use a simple, yet efficient, computer vision system to grasp and move common household objects with a two-channel myoelectric prosthetic hand. Approach. We developed a deep learning-based artificial vision system to augment the grasp functionality of a commercial prosthesis. Our main conceptual novelty is that we classify objects with regards to the grasp pattern without explicitly identifying them or measuring their dimensions. A convolutional neural network (CNN) structure was trained with images of over 500 graspable objects.

Finally, the system was tested with two trans-radial amputee volunteers controlling an i-limb UltraTM prosthetic hand and a motion controlTM prosthetic wrist; augmented with a webcam. After training, subjects successfully picked up and moved the target objects with an overall success of up to 88%.

In addition, we show that with training, subjects’ performance improved in terms of time required to accomplish a block of 24 trials despite a decreasing level of visual feedback. Significance. The proposed design constitutes a substantial conceptual improvement for the control of multi-functional prosthetic hands. We show for the first time that deep-learning based computer vision systems can enhance the grip functionality of myoelectric hands considerably.

A couple of science-fictional predecessors to this idea occur to me.

In his 1941 novel Methuselah's Children, sf author Robert Heinlein writes about a human baby modified by an alien race. The baby was given the following "improvements" (among others):

"...it's body architecture has been redesigned for greater efficiency, our useless simian hangovers have been left out, and its organs have been rearranged in a more sensible fashion. You can't say it's not human, for it is... an improved model. Take that extra appendage at the wrist. That's another hand, a miniature one... backed up by a microscopic eye. You can see how useful that would be, once you got used to the idea."

Trust Robert Heinlein to breathe life into old cliches like "hand-eye coordination".

I'm also fascinated by the idea that robotic hands could be, in effect, independent robots in their own right. Check out the robotic surgeon hand from Philip K. Dick's 1955 short story War Veteran:

From time to time V-Stephens examined his wristwatch and then turned his attention back to the object crawling up and down the sealed edges of the entrance-lock.

The object moved slowly and cautiously. It had been exploring the lock for twenty-nine hours straight; it had traced down the power leads that kept the heavy plate fused in place... During the last hour it had cut its way throught the rexeroid surface to within an inch of the terminals. The crawling, exploring object was V-Stephen's surgeon-hand, a self-contained robot of precision quality usually joined to his right wrist.