Robotics

University researchers make robot breakthrough

30th June 2024
Caitlin Gittins
0

Improving the dexterity of robot hands has remained an ongoing development in the field of robotics as it can have real-world implications for automating tasks such as handling supermarket goods or sorting through waste for recycling.

Led by Professor Nathan Lepora, a team at the University of Bristol has developed a four-fingered robotic hand equipped with artificial tactile fingertips. This hand can rotate objects, such as balls and toys, in any direction and orientation, even when the hand is upside down—a feat that has never been achieved before.

In 2019, OpenAI was the first to demonstrate human-like dexterity with a robotic hand. Despite making headlines, OpenAI soon disbanded its 20-member robotics team. Their setup involved a cage with 19 cameras and over 6000 CPUs to train large neural networks to control the hands, a process requiring substantial financial investment.

Professor Lepora and his team aimed to achieve similar results with more straightforward and cost-effective methods.

Over the past year, four university teams from MIT, Berkeley, Columbia, and Bristol have showcased complex feats of robotic hand dexterity, from picking up and passing rods to rotating children’s toys in-hand, using simple setups and desktop computers.

As reported in the recent Science Robotics article “The future lies in a pair of tactile hands,” the crucial development was integrating a sense of touch into the robotic hands. This was made possible by advances in smartphone camera technology, which are now small enough to fit inside a robot fingertip, enabling the creation of high-resolution tactile sensors.

“In Bristol, our artificial tactile fingertip uses a 3D-printed mesh of pin-like papillae on the underside of the skin, based on copying the internal structure of human skin,” explained Professor Lepora. “These papillae are made on advanced 3D-printers that can mix soft and hard materials to create complicated structures like those found in biology.

“The first time this worked on a robot hand upside-down was hugely exciting as no-one had done this before. Initially the robot would drop the object, but we found the right way to train the hand using tactile data and it suddenly worked even when the hand was being waved around on a robotic arm.”

The future advancements for this technology aim to progress beyond simple pick-and-place or rotation tasks to more sophisticated examples of dexterity, such as the manual assembly of items like Lego.

Professor Lepora’s research has been made possible through a Leverhulme Trust Research Leadership Award.

Featured products

Upcoming Events

View all events
Newsletter
Latest global electronics news
© Copyright 2024 Electronic Specifier