Mixed bio-waste generated along the agri-food value chain is an abundant resource, rich in valuable compounds e.g., polysaccharides or polyphenolic constituents. Yet, its potential as a source of recycled components is untapped - 75% of the generated bio-waste (approx. 85 M/y) is landfilled or incinerated, constituting 3% of total EU GHG emissions. Valorisation of mixed bio-waste from the agri-food sector is hindered by (1) technological challenges of removing impurities (e.g., plastics, cardboard, or metals) that would otherwise decrease the process quality, (2) logistics challenges of collecting seasonal, geographically dispersed feedstock that lower valorisation cost-benefit. MixMatters proposes an innovative system that efficiently separates and valorises three types of mixed bio-waste streams containing impurities from the agri-food industry (wholesale markets, greenhouses, food and drink industry) and obtains six high value-added outputs (powder ingredients, sugar concentrates, recombinant proteins, green fibres, bioactive compounds, plastic monomers). The MixMatters system is modular and multi-purpose - able to treat a range of mixed bio-waste streams (ensuring feedstock supply). The separation stage is automated, integrating advanced robotics and AI. It is also containerised – separating the bio-waste at waste generation sites to avoid inefficient transportation of water and stream spoilage. The system functioning is optimised via a Decision Support while transparency + traceability are ensured via a Digital Product Passport. In the project, the system will be demonstrated during 15 months at three waste generation sites, along with output validation with 6 bio-based industries and active involvement of value chain actors (partner networks outreach + 2,280 members) – to ensure result deployment. MixMatters will contribute to meeting the separation targets of the Waste Framework Directive (separated 6,240 t/y by one system at industrial scale).
Recycleye presents GRIP-R (Gripper Innovation for the Picking of Recyclables), an AI-driven waste sorting solution with enhanced gripping capabilities that will put the country on track to meet the Plastics Pact target of 70% of plastics packaging effectively recycled, and spearhead the mission to optimise the waste industry's ability to handle the growing issue of contamination caused by film and flexible packaging.
Recycleye has already developed a low-cost, AI-powered system replicating the power of human vision. It uses advanced machine learning algorithms to provide automatic, image-based detection of individual items in co-mingled waste streams, at a material and object level. It leverages a cutting-edge synthetic data generation pipeline, and Recycleye's own WasteNet - the world's largest visual database of labelled waste items, with over 2.5 million images across 28 material classes.
In a previously funded R&D project, Recycleye augmented the vision system with a robotic arm to deliver a robotic sorting solution. Now, Recycleye will push the boundaries of robotics to aim for a higher successful pick rate, leading to more accurate industrial processes and purer material streams circulating in the waste industry, while rapidly expanding the waste industry's films and flexibles handling capacity.
It is traditionally unfeasible to detect and sort films and flexible plastic packaging without extensive manual labour (economically unviable) and these materials are often released into the environment through international waste exports or landfilling. Films and flexibles that do find their way into Material Recovery Facility's (MRFs), are stream contaminants, and can cause significant damage to existing machinery, resulting in blockages and downtime which impacts the recovery of high-value target plastics.
GRIP-R will respond to the challenges posed by film/flexible contamination with exploratory work that results in the redesign of our gripping and pneumatics system to increase material recovery efficiency, while bringing to market the UK's first AI-driven, low-cost, multi-stream robotic sorter which is also equipped to pick and separate films/flexibles.
Recycleye has already developed a low-cost, AI-powered system replicating the power of human vision. It uses advanced machine learning algorithms to provide automatic, image-based detection of individual items in co-mingled waste streams, at a material and object level. It leverages a cutting-edge synthetic data generation pipeline, and Recycleye's own WasteNet - the world's largest visual database of labelled waste items.
In a previously funded R&D project, Recycleye augmented the vision system with a robotic arm to deliver a robotic sorting solution. Now, Recycleye will develop and test a novel robotic grasping technology, that will drastically improve picking accuracy (and therefore the efficiency) of Recycleye's current commercial offerings, enabling the application of Recycleye's technology to waste streams beyond Municipal Solid Waste (MSW), whilst providing significant technical development for the wider industrial automation industry,
The method currently used in automation industry when picking objects, is to aim for the centre of the detected object when grasping. This is optimal if the item is flat, however in numerous industrial applications items are crushed and deformed leading to a sub-optimal or failed item pick. By applying the latest computer vision algorithms and techniques to the grasping problem, Recycleye will develop the first optimal grasp prediction technology that can be deployed real-time to maintain accuracy in complex fast-paced industrial applications. This technology has a huge potential for boosting Recycleye's system capabilities within the waste industry, while providing a step forward in grasping technology relevant to a range of industries.
Recycleye presents Project ADER (Automated Detection, Ejection & Recovery), an AI-driven waste sorting solution that will put the country on track to meet the Plastics Pact target of 70% of plastics packaging effectively recycled, and spearhead the mission to increase recycled content across all plastic packaging by increasing the availability of high-quality and consistent recyclate.
Recycleye has already developed a low-cost, AI-powered system replicating the power of human vision. It uses advanced machine learning algorithms to provide automatic, image-based detection of individual items in co-mingled waste streams, at a material and object level. It leverages a cutting-edge synthetic data generation pipeline, and Recycleye's own WasteNet - the world's largest visual database of labelled waste items, with over 2.5 million images.
ADER will leverage AI in order to sort materials to a higher granularity, speed, and affordability than ever possible before. It will sort post-consumer waste into more categories (10+ vs 2-3) than existing optical sorting machines which rely on NIR alone, and so have limited scaling potential due to the sensor's high cost. Moreover, the integration of Recycleye's AI vision module enables the sorting of waste to currently impossible levels of purity and granularity, for example by distinguishing between food and non-food grade PP, PET trays and PET bottles, and can even detect less commonly collected classes, such as coloured plastics (jazz).
Small Business Research Initiative
Project ADER (**A**utomated **D**etection, **E**jection & **R**ecovery) delivers a turnkey waste sorting solution that outperforms the current state-of-the art in recycling technology. ADER utilises cutting-edge computer vision algorithms and a novel air jet ejection system sorting to a higher granularity, speed, and greater affordability than ever possible before. ADER's eyes, combining near-infra-red (NIR) and advanced computer vision algorithms, provide the speed and accuracy of NIR with the granularity and knowledge of the Recycleye AI Vision system. The ejection system, cuts down space, reduces cost, and can sort into more categories than existing NIR machines (10+ vs 2-3). This project is led by Recycleye, a world-leading company in smart AI systems for the waste industry. Recycleye's first product line radically innovated waste detection by leveraging advanced proprietary computer vision algorithms spun-out of PhD research at Imperial College London. At Recycleye we believe waste does not exist -- only material in the wrong place. Project ADER is formed from Recycleye's team of technologists, each with years of industry experience delivering radical new innovations. There are no subcontractors as part of the project as the Recycleye team is perfectly placed to pioneer the next breakthrough for the industry. ADER's development is in two Phases: Phase 1 feasibility studies focus on validating the radical innovation of combining NIR sensors with Recycleye Vision and the novel ADER ejection system. Phase 2 involves data acquisition, further software development, prototype build and industrial testing. This culminates in the production of a commercial system that brings together newly developed IP, harnessing novel technological development to benefit waste facilities in the UK and abroad. _Enhancing the benefits and value of our natural resources_ is the main theme of this project supporting the UK's Clean Growth Strategies, working towards achieving zero avoidable waste by 2050\. Project ADER contributes to this by enabling sorting of entirely new waste materials, increased granularity (sort food-grade vs non-food-grade material) and a radically cheaper system. By optimising the waste industry and improving the recycling rate of materials, ADER is accelerating the UK's transition to a circular economy.
Given all material has value, waste should not exist -- simply materials in the wrong place. Yet, 485m tonnes of material p/a is still not recycled in the UK but sent to landfill, exported abroad, or even worse ends up in the ocean. Currently, the recycling industry relies on large-scale material recovery facilities (MRF) which sort recyclables into usable material (purity = value). However, these require years of planning, large capital investment, numerous expensive machines and still use an agency workforce to manually sort materials. Smaller-scale facilities use manual labour entirely to sort waste as the capital cost for a minimal working MRF is too high.
With this project, Recycleye will disrupt the waste management industry by creating a rapidly deployable, decentralized, scalable, digital & fully-automated sorting solution - mini material recovery facilities (mini-MRF). Recycleye has already developed a state-of-the-art computer vision system using recent advances in deep learning and AI capable of classifying items by material type and brand. The project's key objectives are to augment this vision-system with a robotic arm. A conveyor will carry waste towards the system where the vision unit will detect the different types of recyclables. Then, using a robotic arm the waste types will be sorted into respective piles providing a sorted/pure stream of recyclables that can then be re-injected into the UK economy/ sold to reprocessors.
The project will focus on replicating uniquely human abilities - which machines have up until now not been able to match. The eye: The Recycleye vision system is able to, for example, understand that a piece of cardboard is pizza box (and hence likely food contaminated) even if it is torn, half-hidden by another item and covered in dirt. The arm: A mechanical arm is the most efficient way of removing target materials without having to rely on a material's physical characteristics (densities, ferrousity, form factor, etc). The project will build and test a fully operational mini-MRF ready for mass production.
By developing the low-cost and data-driven sorting solution the recycling industry desperately needs, Recycleye is building the UK's future waste management infrastructure and accelerating the country's transition towards a circular economy.