PRESS RELEASE: Intelligent Software Helps Build Perfect Robotic Hand

Intelligent Software Helps Build Perfect Robotic Hand

Scientists in Portsmouth and Shanghai are working on intelligent software that will take them a step closer to building the perfect robotic hand.

Using artificial intelligence, they are creating software which will learn and copy human hand movements.

They hope to replicate this in a robotic device which will be able to perform the dexterous actions only capable today by the human hand.

Dr Honghai Liu, senior lecturer at the University of Portsmouth’s Institute of Industrial Research, and Professor Xiangyang Zhu from the Robotics Institute at Jiao Tong University in Shanghai, were awarded a Royal Society grant to further their research.

The technology has the potential to revolutionise the manufacturing industry and medicine and scientists hope that in the future it could be used to produce the perfect artificial limb.

“A robotic hand which can perform tasks with the dexterity of a human hand is one of the holy grails of science,” said Dr Honghai Liu, who lectures artificial intelligence at the University’s Institute of Industrial Research. The Institute specialises in artificial intelligence including intelligent robotics, image processing and intelligent data analysis.

He said: “We are talking about having super high level control of a robotic device.

Nothing which exists today even comes close.”

Dr Liu used a cyberglove covered in tiny sensors to capture data about how the human hand moves. It was filmed in a motion capture suite by eight high-resolution CCD cameras with infrared illumination and measurement accuracy up to a few millimetres.

Professor Xiangyang Zhu from The Robotics Institute at the Jiao Tong University in Shanghai, which is recognised as one of the world-class research institutions on robotics, said that the research partnership would strengthen the interface between artificial intelligence techniques and robotics and pave the way for a new chapter in robotics technology.

“Humans move efficiently and effectively in a continuous flowing motion, something we have perfected over generations of evolution and which we all learn to do as babies. Developments in science mean we will teach robots to move in the same way.”

Suggested Articles

Half of patients in an early trial of Allogene's off-the-shelf CAR-T cells for lymphoma who received a higher dose of its antibody ALLO-647 responded.

Takeda is tossing out a Shire pipeline med after it couldn't find a buyer.

Ipsen's new hire arrives at a company reeling from a torrent six months that have crushed hopes for its $1 billion bet on a rare disease drug.