Looks like it could deliver a beating, too.<p>That thing could deliver a punch or get a good grip on a baseball bat.
Just the thing to hook up to a machine learning system.
When it comes to training, software, does physical scale really matter?<p>If you want to train control software for a delicate humanoid hand, why not scale it up two or three times to get robustness, and then have it manipulate equivalently enlarged test objects?<p>I suppose there might be some square-cube law stuff when it comes to catching and throwing...