Researchers have covered robotic fingers with a new artificial skin that allows the hand to grasp fragile pencil lead and pull away from a needle before it punctures the covering. Both actions depend on more than sensitive sensors. The robot must also receive and interpret their signals quickly enough to respond.

Adding thousands of sensing points makes that harder, because more detailed touch information also means more data to read, transmit and process.

Researchers at Southern University of Science and Technology in China and collaborating institutions tackled that bottleneck with a system inspired by the human sensory nervous system. Described in Nature Machine Intelligence, it reads more than 10,000 sensing elements 100 times a second and processes the information in stages.