Engineering news

Robotic finger 'has similar touch sensitivity to humans'

Professional Engineering

The tactile finger progressing through its manufacturing stages: 3D-printed skeleton, flexible circuit board, transparent silicone layer and reflective skin (Credit: Pedro Piacenza/ Columbia Engineering)
The tactile finger progressing through its manufacturing stages: 3D-printed skeleton, flexible circuit board, transparent silicone layer and reflective skin (Credit: Pedro Piacenza/ Columbia Engineering)

A new robotic finger reportedly has touch sensitivity similar to humans.

Created by researchers at Columbia University in New York, the finger can ‘localise’ touch to within 1mm2 thanks to an innovative combination of technologies. It could be used for dexterous robotic manipulation in a range of complex tasks, such as manufacturing or nuclear decommissioning.  

“There has long been a gap between standalone tactile sensors and fully integrated tactile fingers – tactile sensing is still far from ubiquitous in robotic manipulation,” said mechanical engineer and computer scientist Matei Ciocarlie, who led the work with electrical engineer Professor Ioannis Kymissis.

Previous methods for building touch sensors have proven difficult to integrate into robot fingers, the researchers said. Challenges include difficulty in covering curved surfaces, high wire count and difficulty fitting sensors into small fingertips, preventing their use in dexterous hands.

The Columbia team took a new approach, using overlapping signals from light emitters and receivers in the functional areas of the finger. By measuring light transport between every emitter and receiver, they collected a “very rich” data set that changes in response to deformation of the finger due to touch.

Under the ‘skin’, the finger has a layer of transparent silicone, into which more than 30 LEDs shine. The finger also has more than 30 photodiodes that measure how light bounces around inside. Whenever the finger touches something its skin deforms, so light shifts around in the transparent layer underneath. By measuring how much light goes from every LED to every diode, the researchers get close to 1,000 signals, each containing some information about the contact that was made.

The team then use purely data-driven deep learning to extract useful information from the data, including contact location and applied normal force, without the need for analytical models.

The researchers described the result as a “fully integrated, ‘sensorised’ robot finger, with a low wire count, built using accessible manufacturing methods and designed for easy integration into dexterous hands.”

Ciocarlie said: “The human finger provides incredibly rich contact information – more than 400 tiny touch sensors in every square centimetre of skin. That was the model that pushed us to try and get as much data as possible from our finger. It was critical to be sure all contacts on all sides of the finger were covered – we essentially built a tactile robot finger with no blind spots.”

The finger was designed for easy integration onto robotic hands. It needs a 14-wire cable connection, and no complex off-board electronics. The finger already features on two of the team’s dexterous hands, and the researchers will test them in the coming months.

“Dexterous robotic manipulation is needed now in fields such as manufacturing and logistics and is one of the technologies that, in the longer term, are needed to enable personal robotic assistance in other areas, such as healthcare or service domains," said Ciocarlie.

The technology could also be useful in extreme environments, such as nuclear decommissioning or in-orbit satellite construction.

The research was published online in IEEE/ASME Transactions on Mechatronics.


Want the best engineering stories delivered straight to your inbox? The Professional Engineering newsletter gives you vital updates on the most cutting-edge engineering and exciting new job opportunities. To sign up, click here.

Content published by Professional Engineering does not necessarily represent the views of the Institution of Mechanical Engineers. 

Share:

Read more related articles

Professional Engineering magazine

Professional Engineering app

  • Industry features and content
  • Engineering and Institution news
  • News and features exclusive to app users

Download our Professional Engineering app

Professional Engineering newsletter

A weekly round-up of the most popular and topical stories featured on our website, so you won't miss anything

Subscribe to Professional Engineering newsletter

Opt into your industry sector newsletter

Related articles