Can a garbage collecting robot find me a pile of money in a mattress? Can it spare real-life sorters from the dangers of e-waste? Will they take over jobs and a way of life?
Plenty of people the world over rely on livelihoods out of sorting trash. My father did it for years. And I joke to a lot of people that he found me at the side of the road. But the same people and children who pick through trash are also exposed to an overload of toxic chemicals and e-waste. My dad was always burning out the plastics on the copper wire he found and I believe it contributed to the cancer he succumbed to.
Today’s robots can already be programmed to accurately recognize many objects through vision and touch. Tactile information, obtained through sensors, along with machine learning algorithms, enables robots to identify objects previously handled.
But sensing is often confused when presented with objects similar in size and shape, or objects unknown to the robot. Other factors restrictive to robot perception include background noise and the same type of object with different shapes and sizes.
In Applied Physics Reviews, researchers from Tsinghua University in Beijing, China worked to break through the difficulties of robotic recognition of various common, yet complex, items.
Humans possess many different types of touch sensing, one of which is temperature: cold metal, warm wood. The researchers aimed to mimic this ability by designing a robotic tactile sensing method that incorporated thermal sensations for more robust and accurate object detection.
The Chinese team created a layered sensor with material detection at the surface and pressure sensitivity at the bottom, with a porous middle layer sensitive to thermal changes. They paired this sensor with an efficient cascade classification algorithm that rules out object types in order, from easy to hard, starting with simple categories like empty cartons before moving on to orange peels or scraps of cloth.
To test the capabilities of their method, the team created an intelligent robot tactile system to sort garbage. The robot picked up a range of common trash items, including empty cartons, bread scraps, plastic bags, plastic bottles, napkins, sponges, orange peels, and expired drugs.
It sorted the trash into separate containers for recyclables, food scraps, hazardous waste, and other waste. Their system achieved a classification accuracy of 98.85% in recognizing diverse garbage objects not encountered previously. This successful garbage sorting behavior could greatly reduce human labor in real-life scenarios where so much goodness goes to landfill.
Can you train the robot hands to find a pile of money in a mattress or gold hidden in an old shoe? We will keep an eye out for this one but also be mindful of trash sorting communities in the world that depend on upycyling.
Well known trash sorting communities in the world include:
The Zabbaleen (Cairo, Egypt): The Zabbaleen are informal Christian garbage collectors who recycle a significant portion of Cairo’s waste. They have developed an efficient system using pigs too! that sorts and repurposes materials from household waste, making them a critical part of the city’s waste management.
The Catadores (Brazil) are cooperative groups of waste pickers who collect and recycle materials from urban waste. They play a vital role in Brazil’s recycling efforts and have helped formalize the recycling sector. Several movies have been made about the importance of garbage collecting for these people.
The Zero Waste Town (Kamikatsu, Japan) has committed to becoming a zero-waste town by implementing extensive sorting practices. Residents separate waste into 45 different categories to maximize recycling and composting.
The Dharavi (Mumbai, India) is one of Asia’s largest slums but it is a hub for recycling and waste management. Small-scale industries in Dharavi recycle plastics, metals, and other materials, contributing significantly to Mumbai’s waste reduction.
