New ‘Electronic Skin’ Breakthrough could Give Robots a Human-Like Sense of Touch
A revolutionary new sensor, mimicking the human nervous system, is poised to dramatically improve robots’ ability to interact with the physical world, addressing a long-standing challenge in robotics.
Robots have made significant strides in various fields, but a crucial element has remained elusive: a nuanced sense of touch, essential for effectiveness in complex environments requiring delicate manipulation.
For years, researchers have attempted to equip robots with enhanced sensing capabilities, utilizing cameras and othre tools. However, a simple, cost-effective solution has proven difficult to achieve. Now, a team at the University at Buffalo has developed a novel technology that could change that.
The findings, recently published in Nature Communications, detail an “electronic skin” that replicates the way nerves in human hands perceive pressure and movement. “The applications are very exciting,” explains Jun Liu, assistant professor in the University at Buffalo’s Department of Mechanical and Aerospace Engineering. “This technology could be used in manufacturing tasks like assembling products and packaging them-basically any situation where humans and robots collaborate. It could also help improve robotic surgery tools and prosthetic limbs.”
Liu,a core faculty member of UB’s RENEW Institute,led the research team,which included Ehsan Esfahani,associate professor in the same department,several students,and a former PhD student now at the University of Chicago.
The sensor’s key innovation lies in its ability to detect not only pressure but also subtle slip and movement. “Our sensor functions like human skin-it’s flexible, highly sensitive, and uniquely capable of detecting not just pressure, but also subtle slip and movement of objects,” says Vashin Gautham, a PhD candidate and the study’s first author. “it’s like giving machines a real sense of touch and grip, and this breakthrough could transform how robots, prosthetics, and human-machine interaction systems interact with the world around them.”
Researchers successfully integrated the sensing system onto a pair of 3D-printed robotic fingers,mounted on a robotic gripper developed by Esfahani’s group. This integration allows the gripper to dynamically adjust its grip force in response to detected slippage, enabling more complex manipulation tasks. “The integration of this sensor allows the robotic gripper to detect slippage and dynamically adjust its compliance and grip force, enabling in-hand manipulation tasks that were previously difficult to achieve,” Esfahani stated.
to demonstrate the sensor’s capabilities, researchers tested the gripper’s response to a copper weight. The system immediately tightened its grip when it detected an attempt to pull the weight away, showcasing its ability to react in real-time. “This sensor is the missing component that brings robotic hands one step closer to functioning like a human hand,” Esfahani added.
The sensor operates on the principle of the tribovoltaic effect, where friction between two materials generates direct-current (DC) electricity. This innovative approach provides a unique and efficient method for detecting subtle movements.
Crucially,the sensor’s response time is comparable to that of human touch receptors. Tests revealed response times ranging from 0.76 to 38 milliseconds, falling within the typical 1-50 millisecond range for human touch. “The system is incredibly fast, and well within the biological benchmarks set forth by human performance,” Liu noted. “We found that the stronger or faster the slip, the stronger the response is from the sensor-this is fortuitous as it makes it easier to build control algorithms to enable the robot to act with precision.”
The research team is now focused on further refining the system, including integrating reinforcement learning, a form of artificial intelligence, to enhance the robot’s dexterity. This next phase of development promises to unlock even greater potential for robotic manipulation and interaction.
The study was supported by the University at Buffalo Center of Excellence in Materials Informatics. This breakthrough represents a significant step toward creating robots that can not only perform tasks but also feel their way through the world, opening up new possibilities for collaboration, assistance, and innovation.
