Home / Blog / Learning from the Octopus

Learning from the Octopus

Inflatable pinchers enable a soft grip. With them a robot can pick up a variety of soft materials, including pizza dough and rolls. Image credit: Soft Robotics

We pick up an apple with the same ease we pick up dough to prepare our pizza (if you are a cooking buff). Yet, the pressure of our fingers varies greatly depending on the object to pick up. This comes natural to us although there is plenty of work  going on in our brain and in the spinal ganglions, with many sensors involved. Interestingly, there is also quite a bit of what we may call “intelligence” since the brain, unconsciously to us, makes some estimation on the pressure needed based on previous experiences and on an evaluation of uncertainty about what it knows.

A good deal in the ease of picking up things is related to the soft flesh on our fingertips.

This complexity has become apparent to engineers when they had to design a robot to manipulate and pick up different things. This proved to be a challenge. A robot can be designed to pick up a specific object, knowing its shape, texture, size and weight but creating a robot that can autonomously decide on the grip parameters have proved very difficult. Computer vision has helped a lot in “sizing” the objects but picking them up has remained, in general, a challenge. Picking up a chicken egg or a marble egg is quite a different story!

Now a US company, Soft Robotics a spin off of Harvard, has found a solution through the use of soft -smart- materials that in  way mimic the capability of an octopus, probably the best “handler” in nature.

They have developed a slate of products with the food industry in mind. This is an area where objects have many different shapes and textures, with various degree of softness. It is also an area where the “human buyer”, that is us, would be upset to see dents and squeezing.

By using soft inflatable material as pinchers the robotic arm, controlled by a computer receiving information from digital cameras (computer vision) and feedback from sensors, Soft Robotics can handle bakery products (watch the video), strawberries and apples with the same effectiveness and ease.

Thinking of it I am really amaze at how much technology is needed to pick up a single strawberry, and how smart we are without event being aware if it!

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the Industry Advisory Board within the Future Directions Committee and co-chairs the Digital Reality Initiative. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.