A tactile sensing robotic hand inspired by fish fin mechanics enables precise control of grip force, helping robots manipulate fragile objects without visual feedback alone.
Engineers at the University of Texas at Austin have introduced a robotic hand technology called Fragile Object Grasping with Tactile Sensing (FORTE). The system demonstrates such sensitive touch that it can pick up delicate items like potato chips or raspberries without breaking them. The launch is presented as a step toward improving robot dexterity in areas where a light touch is essential, including health care, food processing, and manufacturing.
The benefit of the technology is its ability to handle fragile or slippery objects with precision. Current robots often excel at large motions but struggle with fine movements. By integrating tactile sensing into soft robotic fingers, the UT Austin team claims to give machines a sense of touch that allows them to grasp everyday items carefully, from fruit to medical instruments.
The advantages extend to practical applications. In food processing, sensitive grippers could reduce waste by handling fruits and baked goods more gently. In health care, robots could manage fragile biological samples or surgical tools with greater accuracy. In manufacturing, delicate components such as electronics or glassware could be handled without damage. The system’s slip‑sensing ability further distinguishes it, detecting when an object begins to slide and adjusting grip strength in real time.
The fingers are inspired by the fin‑ray effect found in fish fins and built using advanced 3D printing. Internal air channels act as tactile sensors, shifting pressure as the fingers move. Off‑the‑shelf sensors then provide real‑time feedback, allowing the robot to adjust its grip. In tests with 31 different objects, the system achieved a 91.9 percent success rate in single‑trial grasping, outperforming traditional grippers that rely only on visual feedback.
Reflecting on the breakthrough, assistant professor Lillian Chin explains, “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. Most current force sensors aren’t fast or accurate enough to provide that Goldilocks level of detail. In particular, our sensors operate closer to the timescales of human hand sensors.”
