(Nanowerk News) Researchers from the Munich Institute of Robotics and Machine Intelligence (MIRMI) at the Technical University of Munich (TUM) have developed an automated process for creating soft sensors. This universal measuring cell can be attached to almost any type of object. Applications are envisioned primarily in robotics and prosthetics.
“Detecting and sensing our environment is critical to understanding how to interact with it effectively,” says Sonja Groß. An important factor for interaction with objects is their shape. “It determines how we can perform certain tasks,” said researchers from the Munich Institute of Robotics and Machine Intelligence (MIRMI) at TUM. In addition, the physical properties of objects, such as their hardness and malleability, affect how we perceive and manipulate them, for example.
This research has been published in (“Soft Sensing Skin for Arbitrary Objects: Automated Frameworks”).
Artificial hand: interaction with robotic systems
The holy grail in robotics and prosthetics is the realistic emulation of a person’s sensorimotor skills as they exist in human hands. In robotics, force and torque sensors are fully integrated into most devices. These measurement sensors provide valuable feedback about the interaction of a robotic system, such as an artificial hand, with its surroundings.
However, traditional sensors are limited in terms of customization possibilities. They also cannot attach to arbitrary objects. In short: to date, there has been no process for producing sensors for rigid objects of arbitrary shape and size.
The new framework for soft sensors is presented for the first time
This was the starting point of Sonja Groß and Diego Hidalgo’s research, which they have now presented at the ICRA robotics conference in London. The difference: a soft, leather-like material that wraps things around. The research group has also developed a framework that largely automates the production process for these skins.
It works like this: “We use software to build the structure of the sensory system,” says Hidalgo. “We then send this information to a 3D printer where our soft sensor is built.”
The printer injects a conductive black paste into the liquid silicone. The silicone hardens, but the paste is covered by it and remains liquid. When the sensor is squeezed or stretched, its electrical resistance changes.
“That tells us how much compression or stretching force is being applied to the surface. We use this principle to gain a general understanding of interaction with objects and, in particular, to study how to control artificial hands that interact with these objects,” explains Hidalgo.
What sets them apart: sensors embedded in silicon adapt to the surface in question (such as a finger or hand) but still provide accurate data that can be used for interaction with the environment.
A new perspective for robotics and especially prosthetics
“The integration of this soft, skin-like sensor in a 3D object opens a new pathway for advanced haptic sensing in artificial intelligence,” said MIRMI Executive Director Prof. Sami Haddadin.
The sensors provide valuable data on compression forces and deformations in real time – providing immediate feedback. This extends the range of perception of objects or robot hands – facilitating more sophisticated and sensitive interactions.
Haddadin: “This work has the potential to bring about a general revolution in industries such as robotics, prosthetics and human/machine interaction by enabling the creation of wireless and adaptable sensor technologies for arbitrary objects and machines.”