One key challenge in robotics and prosthetics has been to mimic the intricate sensorimotor skills of humans. In this domain, force and torque sensors, crucial for understanding environmental interaction, are integrated into most robotic systems, such as artificial hands. Despite their utility, conventional sensors have had significant limitations, including the inability to be customized or fitted onto objects with arbitrary shapes and sizes. Until now, a manufacturing process for producing sensors for rigid objects of various shapes and sizes did not exist.
Addressing this gap, researchers Sonja Gross and Diego Hidalgo recently unveiled their groundbreaking work at the ICRA robotics conference in London. The key innovation is the development of a soft, skin-like material capable of enveloping various objects. Additionally, the team has designed a largely automated framework for producing this sensor-infused 'skin'.
Hidalgo explains, "We use software to build the structure for the sensory systems. We then send this information to a 3D printer where our soft sensors are made." In this process, a conductive black paste is injected into liquid silicone, which hardens around the paste, leaving the paste liquid within. As the sensors are compressed or stretched, their electrical resistance alters, providing an indicator of the applied force.
Hidalgo elaborates, "That tells us how much compression or stretching force is applied to a surface. We use this principle to gain a general understanding of interactions with objects and, specifically, to learn how to control an artificial hand interacting with these objects." Notably, the silicone-embedded sensors can adapt to different surfaces, such as fingers or hands, while still providing accurate data for environmental interaction.
MIRMI's Executive Director, Prof. Sami Haddadin, sees far-reaching implications for this development. "The integration of these soft, skin-like sensors in 3D objects opens up new paths for advanced haptic sensing in artificial intelligence," he suggests.
These sensors yield valuable real-time data on compressive forces and deformations, enabling prompt feedback. The perception range of an object or a robotic hand could thus be expanded, allowing more refined and sensitive interaction.
Haddadin further contemplates a broad impact on industries like robotics, prosthetics, and human-machine interaction. "This work has the potential to bring about a general revolution in industries such as robotics, prosthetics and the human/machine interaction by making it possible to create wireless and customizable sensor technology for arbitrary objects and machines," he asserts. As a result, these new flexible, skin-like sensors could herald a new era in the world of robotics and prosthetics.
Research Report:Soft Sensing Skin for Arbitrary Objects: An Automatic Framework
Related Links
Technical University of Munich
All about the robots on Earth and beyond!
Subscribe Free To Our Daily Newsletters |
Subscribe Free To Our Daily Newsletters |