London Recycling Plant Tests Humanoid Robot to Ease Worker Shortages
Dust hangs thick in the air at Sharp Group's busy recycling plant in Rainham, east London, where the constant clatter of hoppers and conveyor belts creates a tough workplace.
The family-run skip and waste management firm processes up to 280,000 tonnes of mixed recycling each year. Its 24 agency workers sort items ranging from shoes and old VHS cassettes to concrete blocks along the fast-moving belts.
The industry carries serious risks. Sharp Group points to its strong safety record, but work-related injuries and illnesses occur 45% more often here than in other sectors. The fatality rate runs several times the national average.
Those hazards, plus the grimy conditions, drive high turnover. Staff leave at a 40% annual rate.
"The belt is moving all the time, you're constantly picking. I go through a lot of pickers because they just aren't up to the job," line supervisor Ken Dordoy said.
The company rotates workers across different materials every 20 minutes and halts the belt at intervals for breaks.
A potential fix for the turnover appeared during a recent visit: a robot named Alpha, short for Automated Litter Processing Humanoid Assistant. Built by RealMan Robotics in China, the humanoid is being adapted for recycling lines by British firm TeknTrash Robotics.
Automated sorters exist in the sector, but humanoids remain rare.
TeknTrash founder and CEO Al Costa said mimicking human motions lets Alpha slot into current plants without machinery overhauls.
Alpha still needs training. Plant workers guide its arm movements while wearing VR headsets to record proper picking and sorting techniques.
The process has two steps: spotting items on the belt and grabbing them. Costa called this standard for early training.
"The market thinks these robots are prêt-à-porter, that all you need to do is to plug them to the mains and they will work flawlessly. But they need extensive data in order to be effectively useful,"
A system called HoloLab feeds data from multiple cameras to Alpha. It alerts the robot to incoming items, directs its arms and flags misses when objects pass unsorted. Thousands of items generate millions of data points daily.
If successful, Alpha could transform operations. "The attraction of a humanoid is that you can put it here and it stays here. It will pick all day, 24 hours a day, seven days a week. It's not going to apply for a holiday, it's not going to have a sick day," said Chelsea Sharp, plant finance director and granddaughter of founder Tom Sharp.
Other firms offer alternatives, like building custom plants or retrofitting with specialized gear. Colorado-based AMP runs three facilities and has equipped dozens more worldwide, including in Europe and the UK.
AMP CEO Tim Stuart said the company uses air jets to direct items into chutes. AI refines identification and sorting over time. "Our robots are much more efficient than humans, probably eight or 10 times the pace. The AI technology and jets have really increased the capacity and efficiency and accuracy of what we can do."
California's Glacier, co-founded by Rebecca Hu-Thrams, employs mounted robotic arms and AI. She noted trash's huge variability as a key hurdle.
Beer cans sometimes spray liquid and damage gear, while customers have found hand grenades and firearms in the mix. "As our models learn from more than a billion items, the AI gets better and better," Hu-Thrams said. "And we've always designed our technology so it works not just for big urban plants, but for the semi-rural facilities running on much tighter budgets."
All three companies say the labor-heavy approach no longer works. Robots ignore dust, noise and hazards, but automation raises questions for human staff.
Sharp said jobs will evolve. "The plan is to upskill those staff. They'll be maintaining and overseeing the robots. And it brings those same people away from any dangers, including the unpleasant environment, heavy lifting and noise."
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Wow
0
Sad
0
Angry
0
Comments (0)