Engineers from the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a new recycling robot that’s capable of automating the process of sifting through trash to distinguish between paper, plastic and metal items. In doing so, it could automate a dull — but entirely necessary — job that few people would want to carry out by hand if there was another option available.
“Although single-stream recycling is really convenient for people, it’s actually a time-consuming and expensive ordeal, requiring significant human labor,” Lillian Chin, a CSAIL Ph.D. student who worked on the project, told Digital Trends. “In developing countries, people have to pick out the recyclable materials from normal waste which can be quite hazardous. [But] even in the U.S., with more automated recycling centers, people are still needed to double-check the machine’s output and manually pick out unrecyclable objects like car engines and plastic bags.”
Chin notes that machines used in these centers are also incredibly specialized. For instance, they use optical sorters that analyze different wavelengths of light to distinguish between plastics or magnetic sorters for filtering out iron and steel products. Even then, they can make mistakes. As a result of challenges like this, the majority of the United States’ single-stream recycling risks being sent to landfills.
The Rocycle robot system may help change this. It’s a sorting robot, which boasts soft Teflon fingers with fingertip sensors that allow it to detect an object’s size and stiffness. The soft fingers help the hand to grasp objects, ensuring a solid grip and sensor readings. The motor-driven and puncture-resistant hands are also robust enough to work with a moving conveyor of recyclable goods without being damaged.
“Rocycle works by using a ‘strain sensor’ to estimate the size of an object, and then uses two pressure sensors to measure the exact force needed to grasp an object,” Chin continued. “These two pieces of information, as well as existing calibration data about the size and stiffnesses of different materials, allows the gripper to predict what material the object is made of. The tactile sensors are [also] conductive, which means they can detect metal by how much it changes the electrical signal.”
Chin said that there currently aren’t plans to commercialize Rocycle, although that could certainly change in the future. The project will continue, however. One innovation the team hopes to add is the ability to combine tactile data with video data, giving Rocycle eyes that will let it perceive the world around it. This should allow it to be made even more nuanced in terms of distinguishing different kinds of materials.
