Laser beams power and guide soft robotic arm

The research from Rice University in Texas could inform new ways to control implantable surgical devices or machines handling delicate objects.

In a proof-of-concept study that integrates smart materials, machine learning and an optical control system, the Rice researchers led by materials scientist Hanyu Zhu used a light-patterning device to precisely induce motion in a robotic arm made from azobenzene liquid crystal elastomer, which is a type of polymer that responds to light.

According to the study published in Advanced Intelligent Systems, the new robotic system incorporates a neural network trained to predict the exact light pattern needed to create specific arm movements, thereby making it easier for the robot to execute complex tasks without needing similarly complex input from an operator.

In a statement, first author Elizabeth Blackert said: “This was the first demonstration of real-time, reconfigurable, automated control over a light-responsive material for a soft robotic arm.”

Conventional robots typically involve rigid structures with mobile elements to enable a predefined range of motion.