RoCycle is, naturally, short for “recycling robot,” the latest offering out of MIT’s CSAIL lab. The pick and place ‘bot utilizes a unique combination of sensors to help distinguish the material differences of objects in order to sort them ahead of the recycling process.
Built on top of a Rethink Robotics Baxter, the system utilizes a Teflon gripper with built in sensors that are capable of determining an object’s makeup based on size and stiffness. It’s not completely perfect just yet.
The technology works thusly:
The team’s gripper first uses its “strain sensor” to estimate an object’s size, and then uses its two pressure sensors to measure the force needed to grasp an object. These metrics – along with calibration data on the size and stiffnesses of objects of different material types – is what gives the gripper a sense of what material the object is made of. (Since the tactile sensors are also conductive, they can detect metal by how much it changes the electrical signal.)
The school notes that it’s got a pretty good 85 percent accuracy rate when attempting to identify stationary objects.
That number drops a good deal down to 63 percent when objects are moving in a conveyor belt-type situation — which is the kind of real-world scenario in which such an object would likely be deployed. Much of the inaccuracy stems from products like cans where an outer paper layer covers tin or aluminum.
The team is working on it by adding more sensors. It also seems likely that such a technology would be used in tandem with existing systems, which use magnets to separate out metals and vision to determine material properties. CSAIL plans to combine the technology with a vision system in its own future experiments.