stub Soft Robot Detects Damage and Heals Itself - Unite.AI
Connect with us

Robotics

Soft Robot Detects Damage and Heals Itself

Published

 on

Image: Cornell University

A team of engineers at Cornell University has developed a soft robot that can detect when and where it was damaged before healing itself right away. 

The research, “Autonomous self-healing optical sensors for damage intelligent soft-bodied systems,” was published in Science Advances. 

Making Robots More Enduring and Agile

Rob Shepherd is an associate professor of mechanical and aerospace engineering. 

“Our lab is always trying to make robots more enduring and agile, so they operate longer with more capabilities,” he said. “If you make robots operate for a long time, they’re going to accumulate damage. And so how can we allow them to repair or deal with that damage?”

The professor’s Organic Robotics Lab was responsible for developing stretchable fiber-optic sensors to be used in soft robots and related components. They can be used in many different ways, including skin and wearable technologies. 

According to Shepard, the first step for self-healing capabilities is to enable the robot to identify that something needs to be fixed. To achieve this, the team created an innovative technique involving fiber-optic sensors paired with LED lights that can detect minute changes on the robot’s surface. 

The sensors are combined with a polyurethane urea elastomer that incorporates hydrogen bonds, which enables rapid healing. There are also disulfide exchanges that increase strength. 

SHeaLDS Self-Healing System

This new system was used to create SHeaLDS, which are self-healing light guides for dynamic sensing. They provide a damage-resistant soft robot that is capable of healing itself from cuts at room temperature, all without any external intervention. 

The researchers installed the SHeaLDS in a soft robot that resembled a four-legged starfish. They then equipped it with feedback control and punctured one of its legs six times. The robot was able to detect the damage and self-heal each cut in about a minute, and it could autonomously adapt its gait based on the sensed damage. 

Despite the material being incredibly sturdy and resistant, it’s important to note that it’s not indestructible. 

“They have similar properties to human flesh,” Shepherd said. “You don’t heal well from bruning, or from things with acid or heat, because that will change the chemical properties. But we can do a good job of healing from cuts.” 

The team will now look to integrate SHeaLDS with machine learning algorithms that can recognize tactile events to create an enduring robot that has self-healing skin. That same skin can also be used to sense its environment and complete a wide range of tasks.  

Alex McFarland is a Brazil-based writer who covers the latest developments in artificial intelligence & blockchain. He has worked with top AI companies and publications across the globe.