We are creating some awesome events for you. Kindly bear with us.

Industrial Robots to Achieve Humanlike Touch with NTU Singapore’s New Software

Researchers from Nanyang Technological University, Singapore (NTU Singapore), have developed a technology, called Dynamis, that makes industrial robots nimbler and almost as sensitive as human hands, able to manipulate tiny glass lenses, electronics components, or engine gears that are just millimetres in size without damaging them. The breakthrough was first published in the top scientific journal Science and went viral on the internet when it could match the dexterity of human hands in assembling furniture.

We have since upgraded the software technology, which will be made available for a large number of industrial robots worldwide. Mastering “touch sensitivity” and dexterity like human hands has always been the holy grail for roboticists, as the programming of the force controller is extremely complicated, requiring long hours to perfect the grip just for a specific task.

– Professor Pham Quang Cuong, NTU Associate Professor

Clients purchasing the latest robots sold will have an option to include this new technology as part of the force controller, which reads the force detected by a force sensor on the robot’s wrist and applies force accordingly: apply too little force and the items may not be assembled correctly while applying too much force could damage the items.

Today, Dynamis has made it easy for anyone to programme touch-sensitive tasks that are usually done by humans, such as assembly, fine manipulation, polishing or sanding. These tasks all share a common characteristic: the ability to maintain consistent contact with a surface. If the human hands are deprived of our touch sensitivity, such as when wearing a thick glove, the researchers would find it very hard to put tiny Lego blocks together, much less assemble the tiny components of a car engine or of a camera used in our mobile phones.

The technology is a technology for force feedback, which is becoming more and more important in the practical use of robotics. The system is advanced, yet easy to use and light enough to be integrated into the standard robot controllers.

Known as “Force Sensor Robust Compliance Control”, the new software powered by Dynamis, a complex Artificial Intelligence (AI) algorithm, requires only a single parameter to be set – which is stiffness of the contact, whether it is soft, medium, or hard. Despite its “simple set-up”, it has been shown to out-perform conventional robotic controllers which required an enormous amount of expertise and time to fine-tune.

This backbone technology was further improved and was first deployed in custom-built robots, such as, which can handle fragile optical lenses and mirrors with human-like dexterity, now used by multiple companies worldwide. Current robots in the market have either high accuracy but low agility (where robots perform the same movements repeatedly such as in a car factory), or low accuracy but high agility (such as robots handling packages of different sizes in logistics).

By deploying this technology, robotics engineers can now imbue robots with both High Accuracy and High Agility (HAHA) on a large scale, paving the way for industrial applications that were previously very difficult or impossible to implement, such as handling and assembly of delicate, fragile objects such as optical lenses, electronics components, or engine gears.

As reported by OpenGov Asia, Singapore’s IT manufacturer and NTU collaborated to enhance local DS&AI education, empowering students with the tech tools and skills needed to inspire a brighter future. The Lab will put together the IT firm’s cutting-edge deep-learning technology with NTU’s global strengths in artificial intelligence and data science, allowing local data scientists and AI experts to pioneer the development of meaningful AI solutions in important industries.

According to NTU, the Lab was still in the planning stages in 2018, and roughly 150 NTU students enrolled in the Bachelor of Science in Data Science and Artificial Intelligence programme have benefited from the Lab’s resources since then.

Send this to a friend