Stanford Researchers Develop Electronic Glove to Give Robots Manual Dexterity

An electronic glove consisting of sensors has been constructed by Stanford engineers, which could soon offer robotic hands the sort of dexterity that humans take for granted.

Stanford researchers have developed sensors to give robotic hands a sense of touch. The sensor shown in this photo is sensitive enough to allow the finger to hold a blueberry without crushing it. In the future all the fingers and the palm would have similar electronic sensors that mimic the biological sensors in our skin. (Image credit: Courtesy of Bao Lab)

In a paper reported in the November 21st issue of Science Robotics, chemical engineer Zhenan Bao and her team show that the sensors function well enough to allow a robotic hand to handle a ping-pong ball without crushing them and touch a fragile berry.

This technology puts us on a path to one day giving robots the sort of sensing capabilities found in human skin.

Zhenan Bao, Professor of Chemical Engineering, Stanford University.

Bao said the sensors in the glove’s fingertips concurrently measure the intensity and direction of pressure, two qualities vital to accomplishing manual dexterity. The scientists must still improve the technology to automatically regulate these sensors but when they achieve that, a robot wearing the glove could have the dexterity to hold an egg between thumb and forefinger without smashing it or dropping it.

Electronics imitating life

The electronic glove mimics the way layers of human skin function together to offer human hands their amazing sensitivity.

The outer layer of the human skin is imbued with sensors to detect heat, pressure, and other stimuli. Human fingers and palms are especially rich in touch sensors. These sensors function along with a sub-layer of skin known as the spinosum, an uneven microscopic terrain of hills and valleys.

That uneven feature is critical. When the fingers touch an object, the outer layer of the skin moves closer to the spinosum. A light touch is felt mostly by sensors near the hilltops. More strong pressure forces the outer skin down into the valleys of the spinosum, activating more intense touch sensations.

However, measuring the intensity of pressure is only part of what the spinosum enables. This uneven sub-layer also helps expose the direction of pressure, or shear force. A finger pressing north, for example, forms robust signals on the southern slopes of those microscopic hills. This ability to sense the shear force is part of what helps a person to lightly but firmly hold an egg between thumb and forefinger.

Postdoctoral scholar Clementine Boutry and master’s student Marc Negre led the creation of the electronic sensors that imitate this human mechanism. Each sensor on the fingertip of the robotic glove is composed of three flexible layers that function in concert. The bottom and top layers are electrically active. The scientists laid a grid of electrical lines on each of the two facing surfaces, like rows in a field, and turned these rows perpendicular to each other to form a dense array of small sensing pixels. They also made the bottom layer uneven like the spinosum.

The rubber insulator in the middle just kept the bottom and top layers of the electrodes apart. But that separation was crucial, as electrodes that are close but do not touch can store electrical energy. As the robotic finger pressed down, squeezing the upper electrodes closer to the bottom, the volume of the stored energy increased. The hills and valleys of the bottom layer offered a way to map the strength and direction of pressure to particular points on the perpendicular grids, a lot like human skin.

Delicate touch

In order to test their technology, the scientists put their three-layered sensors on the fingers of a rubber glove, and slipped a robotic hand into the glove. Ultimately the goal is to insert sensors directly into a skin-like covering for robotic hands. In one experiment, they automated the glove-wearing robotic hand to gently touch a berry without squishing it. They also automated the gloved hand to lift and move a ping-pong ball without crushing it, by using the sensor to detect the suitable shear force to hold the ball without dropping it.

Bao said that with accurate programming a robotic hand wearing the present touch-sensing glove could do a repetitive task such as lifting eggs off a conveyor belt and putting them into cartons. The technology could also be used in robot-assisted surgery, where precise touch control is vital. But Bao’s ultimate goal is to build a cutting-edge version of the glove that automatically applies just the appropriate amount of force to handle an object carefully without prior programming.

“We can program a robotic hand to touch a raspberry without crushing it, but we’re a long way from being able to touch and detect that it is raspberry and enable the robot to pick it up,” she said.

Zhenan Bao, the K.K. Lee Professor in the School of Engineering, is a professor of chemical engineering, a senior fellow at the Precourt Institute for Energy, a member of Stanford Bio-X, an affiliate of the Stanford Woods Institute for the Environment, and a member of the Wu Tsai Neurosciences Institute. Other Stanford co-authors include Oussama Khatib, professor of computer science; postdoctoral research fellow Orestis Vardoulis; and PhD student Mikael Jorda.

This research was supported partly by the Swiss National Science Foundation, the European Commission, the National Science Foundation and the Stanford Nano Shared Facilities.

Robot gently touches a raspberry

View video of robot touching raspberry

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.