Advancements in soft skin robotics and touch sensors have opened a new realm of possibilities for more intuitive and safer robotic human interaction. The primary issue is the price and complexity involved in manufacturing these technologies. The solution could lie in a novel discovery. A recent study uncovered that soft skin pads, which double as sensors, can be efficiently made from thermoplastic urethane using 3D printers.
Under the guidance of project lead Joohyung Kim, an electrical & computer engineering professor at the University of Illinois Urbana-Champaign, new understandings of the relationships between robots and humans have developed. "Robotic hardware can involve large forces and torques, so it needs to be safeguarded if it's going to directly interact with humans or be used in human environments," Kim detailed. He believes that soft skin will play an instrumental role in mechanical safety compliance and tactile sensing.
The IEEE Transactions on Robotics journal disclosed that the 3D-printed pads serve dual functionality. In addition to being soft skin for a robotic arm, they also work as pressure-based mechanical sensors. The pads exhibit an airtight seal and connect to pressure sensors. When the pad comes into contact with an object, it deforms, much like a squeezed balloon, and the displaced air activates the pressure sensor.
Kim explained, "Tactile robotic sensors often contain intricate arrays of electronics and are considerably high in cost. However, our research shows that practical, durable alternatives can be made inexpensively. Since it's simply a matter of reprogramming a 3D printer, this technique can be easily adapted to various robotic systems."
The team demonstrated the natural use of functionality for safety: if the pads detect an obstacle near a dangerous area such as a joint, the arm halts operations. They also serve operational functionality where the robot interprets touches and taps as instructions.
Since 3D-printed components are relatively inexpensive and simple to manufacture, they can easily be adapted to new robotic systems and replaced when needed. Applications where cleaning and maintenance of parts are expensive or impractical can significantly benefit from this feature.
Kim envisages a future where soft-skinned robots assist in complex environments such as hospitals. "These robots would need to be regularly sanitized, or the skin would need to be replaced often. 3D printing is a scalable process, therefore, interchangeable parts can be produced inexpensively and easily fitted onto the robot body," he explained.
This breakthrough signals a new chapter in robotic sensing and control. Kim envisions that this easy manufacturing technique will fuel further interest and development in the field. "Currently, computer vision and language models are the predominant ways humans interact with robotic systems, but there is a need for more data on physical interactions, or 'force-level' data," Kim mentioned.
From the robot's perspective, this kind of information is the most direct interaction with its environment but very few users -- mostly researchers -- consider it. Kim and his team see the collection of this force-level data as their upcoming task, opening doors for more nuanced robotic interactions in the future.
Disclaimer: The above article was written with the assistance of AI. The original sources can be found on ScienceDaily.
