TeknTrash Robotics, a UK-based company pioneering AI powered robotics and motion intelligence for waste management, has partnered with leading environmental services provider Sharp Group to begin real-world testing of ALPHA – an advanced humanoid robot designed to transform how we sort waste.
Through this, at Sharp Group’s state-of-the-art facility in Rainham, East London, they handle and process 2,800 tonnes of waste a week, which includes plastic, paper, glass, metal, general, stone and more – ideal for developing new technology to assist with waste segregation. Frontline workers are now equipped with Meta Quest 3 headsets that record their movements during daily operations. Using an app developed by TeknTrash, Sharp Group workers are capturing detailed motion data – including posture, hand and finger articulation, and synchronised video – to train next-generation AI robotic models.
This data will then be used in ALPHA (Automated Litter Processing Humanoid Assistant), a new class of humanoid robot capable of taking over waste selection tasks that are repetitive, unsanitary and hazardous.
In fact, the waste and recycling sector is among the most hazardous industries in the UK: in the 2018/19 period, 4.5 percent of workers in this sector suffered from work-related ill health, a figure notably higher than the all-industry average of 3.1 percent. Additionally, the rate of non-fatal workplace injuries stood at 3.4 percent, surpassing the 1.8 percent average across all industries.
Alarmingly, the sector’s fatal injury rate is 17 times higher than the all-industry average, with seven fatal injuries reported in 2018/19 Also, humans sort waste at an average rate of 30 to 40 picks per minute, but fatigue and decision fatigue lead to errors. Contamination items mixed with recyclables remains a persistent issue, with single-stream recycling (where all recyclables are collected in one bin) resulting in about 25 percent of material being contaminated, rendering it unsellable. In 2022, England dry recycling declined by 7.1 percent (0.4 million tonnes), partly due to quality issues affecting resale value.
Robots, by contrast, achieve higher purity rates, reducing bale rejection rates and boosting profitability. And this is where ALPHA plays a role, by working anywhere waste is being handled: initially picking it up from the conveyor belts in recycling plants, and later carrying garbage cans to the truck, lifting up weights in processing plants, etc. As such, at this stage, ALPHA is being trained to identify waste from conveyor belts at recycling plants, selecting them by material (paper, plastic, etc.) and by brand. Unlike traditional solutions that use stationary robotic arms, ALPHA is built for mobility, dexterity, and perception – trained to mirror human hands and precision.
“Our goal is to build a smarter, more sustainable future where waste isn’t just managed—it’s understood,” said Al Costa, chief executive officer at TeknTrash. “We plan to deploy the same solution in 1,000 plants all across Europe, all connected to the cloud, in order to build a huge dataset of actions related to recycling so we can deploy in ALPHA. Through partnerships like this, we’re turning advanced robotics into real-world sustainability impact.”
A Smarter, Safer, Scalable Solution
ALPHA is trained using real-time motion data collected from recycling operatives via VR headsets and the data is sent in real time to cloud servers. The data is then processed through IsaacLab and deployed to NVIDIA’s GR00T framework for real-time inference. And, by shifting computationally intensive tasks like image recognition and movement planning to a centralized cloud server, the robot can run on lightweight, energy efficient hardware – extending battery life and improving runtime reliability. Equipped with hyperspectral vision placed at the start of the conveyor belt, ALPHA tracks waste items earlier and more accurately than solutions which use regular RBGD cameras. Finally, unlike suction-based systems, ALPHA’s grippers, trained through VR to mirror human hand dexterity, are able to grab more waste and, thus, increase recycling rates.
The humanoid system moves autonomously along rails, coordinates with multiple units, and adapts dynamically to operational conditions. This design solves common problems in traditional waste sorting robotics– lack of flexibility, poor accuracy, and high maintenance– while setting a new standard for industrial humanoid applications.
Real-World Impact, Right Now
“We’re thrilled to be working with TeknTrash on such an innovative and forward-thinking project,” said Chelsea Sharp, director at Sharp Group. “The integration of AI and robotics into waste management has the potential to completely transform the industry. Not only will this technology make recycling faster and safer, but it also opens up incredible possibilities for improving transparency and accountability through detailed waste data. We’re proud to be part of something that could truly reshape how the world thinks about waste.”
Waste Data as a Sustainability Superpower
In addition to automation, ALPHA enables real-time, item-level waste data collection. With accurate insights across the waste stream, recycling operators and policymakers can:
- Comply with Extended Producer Responsibility (EPR) regulations
- Track material flows from cradle to grave
- Conduct detailed carbon accounting
- Support circular economy strategies with evidence-based decisions
- Improve ESG and sustainability reporting
Published June 2025
