7 Comments
User's avatar
Abdulrazaq Surakat's avatar

Yeah as of now, visual sensors seem to be the goal, they are scalable and the data is easily interpretable. It would make sense to continue to focus of visual sensors until we figure out a way to more easily interpret the data from tactile sensors.

Expand full comment
Jeremy Cook's avatar

One might argue that IMUs are a form of touch sensing (or at least can be), as are limit switches/sensors on pneumatics or CNC operations.

As for the more human-like touch behavior, perhaps its something that will be pursued once we get closer to the limits of other sensing technologies. I.e. if improved vision sensing is easier right now, I suppose it will be pursued until there's a reason to move on.

Vulcan looks pretty rad though!

Expand full comment
Chris Paxton's avatar

I definitely think vision is enough for a while (or vision + force/torque sensors). I do think anti-slip is a great use case where there's not really anything better than real tactile though.

Expand full comment
Vimal Mollyn's avatar

"but you will almost never have tactile feedback" - you might want to check out Fluid Reality, https://www.fluidreality.com, which provides a way to provide tactile feedback during teleop!

Expand full comment
Chris Paxton's avatar

Cool, i definitely think there are ways to give tactile feedback, they're just not common yet! Will check it out

Expand full comment
Philip Fung's avatar

Fantastic overview as always!

Expand full comment
Chris Paxton's avatar

Thank you!

Expand full comment