People with prosthetic arms teach the robots how to feel and touch like people.
It is hoped that the tests will improve their dexterity for delicate tasks, such as capturing, using real-world data from humans.
ABB Robotics announced a collaboration with California-based bionics company PSYONIC.
ABB’s GoFa collaborative robot – or cobot – will use the PSYNOIC capability prosthetic hand.
He will explore how touch and movement data generated through the use of prosthetics can help train robots to perform variable tasks that are difficult to automate.
Marc Segura, president of ABB Robotics, said: ‘Human dexterity and the instinctive understanding of how to handle different objects is one of the hardest things to replicate in industrial-scale robotics, but it is a crucial need for truly autonomous and versatile robots.
“As we develop the next generation of physical artificial intelligence, robots will learn and understand the world just like we do. This collaboration with PSYONIC will help close the long gap between human and robot dexterity, opening new opportunities for a wide range of industries.’
The firms say grasping and dexterity are key components of ABB Robotics’ vision for versatile Autonomous Robotics, in which robots are capable of sensing, reasoning, moving and manipulating objects with precision in dynamic environments.
Commissioning of robots
Technology is also seen as an important step towards physical advancement artificial intelligence in industry, enabling robotic systems to learn from real-world interactions and reliably apply that knowledge in industrial environments.
ABB and PSYONIC believe the technology could eventually be used in a variety of sectors, including automotive manufacturing, aerospace, packaging and logistics, and life sciences.
The companies say it could allow robots to take on repetitive, physically demanding tasks JOBS and jobs that are difficult to perform consistently on a large scale, helping to improve productivity, flexibility and workplace safety.
Originally developed as a prosthetic device, the PSYONIC Ability hand combines myoelectric control, tactile sensation and compliant mechanics in a lightweight design featuring multiple articulating joints.
The hand includes pressure sensors and vibration feedback technology that enables users to detect contact, grip strength and object release. Its flexible fingers can also naturally adapt to irregularly shaped and deformable objects.
Dr. Aadeel Akhtar, Founder and CEO of PSYONIC, said: ‘Agile manipulation is ultimately as much a data challenge as a hardware challenge.
“Using the same Dexterity Hand in humans and robots, we can capture real-world data on movement, contact and grip strength, and then use that to train robotic systems more effectively.”
He added: “Integrating with the ABB Robotics robotics platform allows us to expand into more environments and unlock the level of agility needed to meet the toughest challenges in automation.”
ABB said its GoFa cobot provides the precision and repeatability needed to translate human-derived manipulation data into consistent robotic actions.
The company believes this level of accuracy is essential for reliably reproducing subtle changes in grip force, finger positioning and movement throughout complex industrial tasks.
The collaboration will assess how the combined technologies can be applied in situations where conventional robotic grippers struggle, particularly when handling fragile, irregularly shaped or highly variable objects.
