Robot Hand With Sensitive Touch Can Gently Grasp Fragile Objects | Futurity

A robotic hand developed at the University of Texas at Austin demonstrates a remarkable level of sensitivity, capable of grasping objects as delicate as a potato chip or a raspberry without causing damage. This advancement, detailed in a recent paper published in IEEE Robotics and Automation Letters, could significantly impact industries requiring precise handling of fragile items, from healthcare to food processing.

The technology, dubbed Fragile Object Grasping with Tactile Sensing (FORTE), isn’t about creating a hand that *looks* like a human hand, but one that mimics the nuanced sensory feedback humans rely on when interacting with the world. Currently, robots excel at large-scale movements but struggle with the fine motor skills needed for delicate tasks. “Robots can fold a shirt but may struggle to carefully pick up your glasses or unpack fruit from your groceries,” explains Siqi Shang, lead author of the study and a doctoral student at UT Austin. UT Austin News reports that the goal is to equip robots with a “sense of touch” to handle objects with greater care.

Inspired by Fish Fins and Advanced 3D Printing

The design of FORTE’s fingers draws inspiration from the “fin-ray effect,” a structural principle found in fish fins. These fingers are created using advanced 3D-printing techniques, incorporating internal air channels that function as tactile sensors. As the fingers close around an object, these channels shift, causing changes in air pressure. Small, commercially available sensors detect these pressure variations, providing the robot with real-time feedback on the force being applied and whether the object is slipping. This allows for adjustments to the grip, preventing crushing or dropping.

Researchers extended the application of this sensing technology through a year-long collaboration with the College of Fine Arts’ theatre and dance department at UT Austin, suggesting potential applications beyond industrial settings. The team tested the grippers on a diverse range of 31 objects, including fragile produce like raspberries and potato chips, slippery items like jam jars and billiard balls, and common household items like soup cans, and apples. The results were promising: the system achieved a 91.9% success rate in single-trial grasping experiments, significantly outperforming traditional grippers that rely solely on visual information.

Precision in Slip Detection

Perhaps even more impressive is the system’s ability to detect slips. FORTE accurately recognized 93% of slip events with 100% precision, meaning it never incorrectly identified a slip. This high level of accuracy is crucial, as it allows the robot to adjust its grip only when necessary, avoiding unnecessary force that could damage the object. Lillian Chin, assistant professor of electrical and computer engineering at UT Austin, emphasizes that humans naturally adjust their grip based on subtle sensory feedback. “Humans pick up objects with just the right amount of force; too much and you’ll crush it, but too little and it’ll slip out of your hand,” she explains. FOX 7 Austin highlights that current force sensors often lack the speed and accuracy to replicate this “Goldilocks” level of control.

Beyond speed and accuracy, the FORTE fingers offer durability and customization. Because they are 3D-printed, the sensors can be easily adapted to various shapes and sizes. The slip-sensing capability is particularly noteworthy, as it’s a feature lacking in many existing robotic gripping technologies.

Implications Across Industries

The potential applications of FORTE are broad. In the food processing industry, more sensitive robotic handling could reduce waste and improve efficiency when dealing with delicate fruits, vegetables, and baked goods. In healthcare, robots equipped with FORTE could precisely handle medical instruments or fragile biological samples. Manufacturing could benefit from the technology’s ability to manipulate delicate components like electronics or glassware. A demonstration on YouTube showcases the hand’s gentle grasp on a variety of objects.

Open-Source Designs and Future Development

To accelerate innovation in this field, the researchers have publicly released the hardware designs and algorithms for FORTE on GitHub. Ongoing research focuses on refining the technology, specifically addressing sensitivity to temperature fluctuations and improving the robot’s ability to recover from slips. The research was supported by a range of organizations, including the Texas Robotics Industrial Affiliate Program, the National Science Foundation, and the Office of Naval Research.

The development of FORTE represents a significant step toward creating robotic hands with dexterity approaching that of humans, opening up new possibilities for automation and assistance in a variety of fields.