undefined | Better HN

0 pointsimtringued10mo ago0 comments

I think you're misunderstanding the essence of the problem. If you use tendons, you'll need a neural network in your control loop that can learn continuously so that it compensates rope stretch and changes in friction through wear and tear.

A lot of problems in robotics reduce down to continual learning. Essentially all system identification tasks become obsolete the moment you have a self learning system and yet we have an AI industry preaching that AGI is around the corner without this "crutch".

0 comments

stefanka10mo ago

Not to mention that they easily break and are annoyingly tedious to be replaced (I had to assist often enough on such "surgeries" in our lab)

stefanka10mo ago

You don't necessarily need neural networks for that, there are more specialized function approximations that learn faster and enable life-long learning for kinematics/dynamics and extrapolate better than NN which are more general purpose.

amelius10mo ago

You could add encoder patterns to the tendons, like stripes. And then use something like a mouse-sensor to track them. This is still much lighter than servos.

Another idea is to use an external camera or two and to track the fingers with a deep learning model. But this can become messy if other objects are in view. And it might also introduce more control delay in the feedback loop than a simple sensor.

stefanka10mo ago

If space permits you should add absolute encoders in the joints. In a finger that’s likely a challenge. In an arm, that’s easy

spauldo10mo ago

I would think pressure and angle sensors tied to a PID loop would suffice, but I'm not a roboticist.

stefanka10mo ago

If you can get a feedback loop at the respective joint, then yes, this might be enough. In case of an arm (not this hand), you can often only observe the end of a chain, and then, that’s more complex

j / k navigate · click thread line to collapse

0 comments

stefanka10mo ago

Not to mention that they easily break and are annoyingly tedious to be replaced (I had to assist often enough on such "surgeries" in our lab)

stefanka10mo ago

amelius10mo ago

You could add encoder patterns to the tendons, like stripes. And then use something like a mouse-sensor to track them. This is still much lighter than servos.

stefanka10mo ago

If space permits you should add absolute encoders in the joints. In a finger that’s likely a challenge. In an arm, that’s easy

spauldo10mo ago

I would think pressure and angle sensors tied to a PID loop would suffice, but I'm not a roboticist.

stefanka10mo ago

j / k navigate · click thread line to collapse