RIT Develops AI-Powered Textile Recycling System

A research team at RIT’s Golisano Institute for Sustainability (GIS) has developed a fully automated system to identify, sort, and disassemble garments at high speed and in high volume, addressing a critical global waste problem.

Led by program manager Mark Walluk, the team includes staff engineers Ryan Parsons, Nick Spears, Sri Priya Das, Ronald Holding, and Christopher Piggot, as well as associate research professor Abu Islam. They are using an automated system to detect and remove non-recyclable elements, enabling higher-value material recovery.

High-Resolution Imaging and AI Integration

The process starts with a conveyor-fed imaging station where three specialized cameras generate a high-resolution, multi-dimensional map of the garment. This allows for fiber composition analysis down to the millimeter level. The system then leverages artificial intelligence and machine vision to identify and remove non-recyclable elements from clothing.

"In traditional manufacturing, these automations have been used for decades and it’s predictable," said Islam, who collaborated with Das on the AI integration. "You know what part is coming next and exactly where it goes. In used clothing, every item is different. That unpredictability means the system must make on-the-spot decisions."

Vision-Guided Algorithms and Robotic Precision

Islam and Das developed vision-guided algorithms that identify features like logos, collars, and cuffs, and interpret infrared reflections to define fiber type. This data is passed to a robotic laser-cutting system that cuts these features with precision and speed, without damaging reusable material. Once cut, the garment advances to a robotic sorting gantry, which places the clean material into separate bins for recycling. The prototype can process a new garment roughly every 10 seconds.

Scalable and Economical Solution

Walluk noted that the system was built with scalability and real-world complexity in mind, making it both economical and ready to replicate.

"It’s not going to solve the world’s textile waste problem, but it’s a step toward a more circular economy," Walluk said. "Today, recyclers prefer post-industrial fabrics because of their predictable material properties. We’re working to advance beyond that step by transforming post-consumer clothing into high-quality, reliable feedstock. This makes these materials not only viable but preferable, helping divert them from landfills."

Key Collaborators and Funding

Key collaborators include Ambercycle, a Los Angeles-based company pioneering polyester recycling, and Goodwill of the Finger Lakes, which provided garments for testing and insights into the resale and reuse market. Nike contributed industry guidance in the project’s early stages. The work, which began in 2023, was funded through a grant of nearly $1.3 million from the REMADE Institute, a public-private partnership focused on developing circular manufacturing solutions. The team presented its work at a global REMADE conference in Washington in April.

Global Impact and Future Prospects

"Textile recycling is a critical global challenge, and we’re proud to collaborate with industry leaders to drive meaningful solutions," said Nabil Nasr, director of GIS and CEO of the REMADE Institute. "This effort not only creates significant environmental impact but also represents a major area of growth and innovation for us at GIS."

Though still in the pilot phase, the technology is already attracting interest globally from recyclers in the US, Europe, South Asia, and Latin America. The team anticipates transitioning the system to its partners for continued testing and potential deployment later this year.