By Stephen Beech via SWNS
A new robot mimics the human sense of touch to sort through trash.
The system achieved a 98.85 percent accuracy rate in recognizing various domestic waste items, say scientists.
They believe the state-of-the-art automaton could eventually lead to better treatments for people with hand disabilities.
The Chinese research team explained that tactile sensing and logical reasoning aided the robot’s ability to recognise and classify objects.
They say today’s intelligent robots can accurately recognize many objects through vision and touch.
Tactile information, obtained through sensors, along with machine learning algorithms, enables them 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, but with different shapes and sizes.
Researchers at Tsinghua University in Beijing worked to break through the difficulties of robotic recognition of several common, yet complex, items.
Study author Professor Rong Zhu said: “Humans possess many different types of touch sensing, one of which is thermal feeling.
“This allows us to sense the wind blowing, perceive hot and cold, and discriminate between matter types, such as wood and metal, because of the different cooling sensations produced.”
The Chinese research team aimed to mimic that ability by designing a robotic tactile sensing method that incorporated thermal sensations for more robust and accurate object detection.
Zhu said: “We propose utilizing spatiotemporal tactile sensing during hand grasping to extend the robotic function and ability to simultaneously perceive multi-attributes of the grasped object, including thermal conductivity, thermal diffusivity, surface roughness, contact pressure, and temperature.”
The 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 the sensor with an efficient cascade classification algorithm that rules out object types in order from easy to hard, starting with simple categories – such as empty cartons – before moving on to orange peel or scraps of cloth.
To test the capabilities of their method, the researchers created an intelligent robot tactile system to sort household garbage.
The robot picked up a range of common trash items, including empty cartons, scarps of bread, plastic bags, plastic bottles, sponges, napkins, orange peels and out-of-date drugs.
It sorted the litter into separate containers for recyclables, food scraps, hazardous waste, and other waste.
‘Their system achieved a classification accuracy of 98.85 percent in recognizing various waste items not encountered previously, according to the findings published in the journal Applied Physics Reviews.
Zhu said: “This successful garbage sorting behavior could greatly reduce human labor in real-life scenarios and provide a broad applicability for smart life technologies.”
He says future research will focus on enhancing robotic embodied intelligence and autonomous implementation.
Zhu added: “In addition, by combining this sensor with brain-computer interface technology, tactile information collected by the sensor could be converted into neural signals acceptable to the human brain, re-empowering tactile perception capabilities for people with hand disabilities.”
