The row cycle system.

My M I t.

Has a soft, puncture resistant hand pressure sensors on his fingertips, detecting objects size and material.

It then autonomously places the item in the appropriate recycle bin computer vision alone.

The systems are not able to separate paper from plastic.

Any paper and plastic cups look the same.

But by introducing the ability to squeeze the the object and to know whether it's flexible or not, we are able to go once that beyond what today's methods can do.

The goal of the system is to reduce the back end cost of recycling.

The company has 85% accuracy in identifying stationery items, but only 63% accuracy on a simulated conveyor belt.

A common error was identifying paper covered tins as paper.

For how research is looking To improve the system, we plan to create a much more detailed centralized skin.

We plan to develop the hand at different sizes and we plan to improve our algorithms for recognition.

We're very excited to see the use of robots automation in solving a problem that matters globally.

The row cycle system by M.

I t has a soft, puncture resistant hand pressure sensors on his fingertips, detecting objects, size and material.

The company has 85% accuracy.

Identifying stationery items only 63% accuracy on a simulated conveyor belt.

We plan to develop the hand at different sizes, and we plan to improve our algorithms for recognition.

We're very excited to see the use of robots automation in solving a problem that matters global.

I thanks for watching all the way to the end of the video.

I hope you enjoyed it.

If you want even more great content, we've got plenty more videos on the channel, so subscribe and you'll never miss a thing.