Robotic scientists are developing a recycling robot which boasts of a robot arm that has soft grippers and has the capabiliy of identifying objects through touch.
MIT's Computer Science and Artificial Intelligence Lab (CSAIL) developed tactile sensors on the robot. The arm is powered electrically and can identify which is paper, metal, and plastic.
"Although environmental and sustainability concerns have made it crucial to scale up recycling operations, object sorting remains a critical bottleneck for recycling scalability," they wrote in their paper that describes their work.
Nothing could be better said than what MIT Technology Review expressed, "the way we sort waste needs to get much better." Douglas Heaven said that "Many large recycling centers already use magnets to pull out metals, and air filters to separate paper from heavier plastics. Even so, most sorting is still done by hand. It's dirty and dangerous work."
The robot team demonstrated that automated recycling requires the natural solution of soft robotic grippers.
"Failure to properly sort materials for recycling leads to waste; in the United States, 25% of all recycled materials are so contaminated they must be sent to landfills."
The concern is that most facilities still resort to manual labor to grasp and sort objects that cannot be sorted automatically. They said, "This can lead to unsafe working conditions, especially in facilities where normal waste is mixed with recyclables."
The team named the recycling robot as RoCycle. Automated recycling can transform the process into facilities. "This classifier works over a variety of objects," they wrote, "including those that would fool a purely vision-based system." RoCycle has embedded tactile sensors that can identify the material it is dealing with.
Strain sensors, high deformation capacitive pressure, and a pair of cylinders comprise the gripper components.
RoCycle does not rely on vision. It can detect a metal by detecting its conductivity. "Our materials classifier has 85 percent accuracy with a stationary gripper and 63 percent accuracy in a simulated recycling pipeline."
The team plans to increase the sorting accuracy of the robot.
