In order to perform tasks that involve moving or manipulating objects, robots should quickly adapt their comprehension and handling strategies based on the properties of these objects and the environment.
Most robotic hands developed so far, however, have a fixed and limiting structure. Thus, they can perform a limited number of movements and can only understand specific types of objects. But this robot finger changes things.
Researchers at the University of Science and Technology in Hong Kong have developed recently a robotic finger tip that can change shape and switch to three different configurations, which could allow it to understand a wider variety of objects. The unique design of the fingertip, presented in a paper presented at this year’s IEEE International Conference on Automation Science and Engineering (CASE), is inspired by origami, the famous Japanese art of folding paper.
What good is a robot finger?
“Our study was inspired by two common observations in current research and industrial applications,” Zicheng Kan and Yazhan Zhang, two of the researchers who conducted the study, told TechXplore. “The first refers to parallel joints developed in previous research studies, which could help achieve industrial automation. These clamps require well-selected clamping points, otherwise a static balance may not be achieved.
Researchers have been trying to develop techniques to control the positions of robotic fasteners for decades. However, most existing approaches have significant limitations. The first goal of the study by Kan, Zhang, and their colleagues was to develop a fingertip that could be easily controlled and performed a variety of actions.
The robotic design of the robot fingertips created by Kan, Zhang and their colleagues is based on other robotic structures presented in their previous studies. In 2019, for example, researchers created a soft, monolithic origami-inspired device with a flat fingertip. While this grip can deform and change shape, its performance in terms of payload and dexterity is poor due to the flatness and softness of the fingertips.
In general, they found that the fingertip they developed has many advantageous features, including the ability to quickly switch between different grip modes, as well as between stable, task-based comprehension modes. The configuration of the fingertip is simulated and efficiently guided by the kinematic model they used.