Grantee Research Project Results
Robotic, Artificial intelligence (AI) Powered Trash System for Facility Sorting and Auditing Waste and Educating Transient Populations
EPA Contract Number: 68HERC23C0004Title: Robotic, Artificial intelligence (AI) Powered Trash System for Facility Sorting and Auditing Waste and Educating Transient Populations
Investigators: Yhap, Charles
Small Business: CleanRobotics, Inc
EPA Contact: Richards, April
Phase: II
Project Period: October 21, 2022 through October 20, 2024 (Extended to October 20, 2025)
Project Amount: $370,130
RFA: Small Business Innovation Research (SBIR) Phase II (2023) Recipients Lists
Research Category: SBIR - Homeland Security , SBIR - Air Quality , SBIR - Sustainability , SBIR - Air
Description:
CleanRobotics has developed a robotic, artificial intelligence (AI) powered system, called TrashBot, for sorting and auditing recycling, landfill, and compost from facilities with transient populations. Our system has the unique capability of ensuring proper waste sorting of up to four waste streams with the added cost reduction of eliminating user intervention. Discarding waste becomes an educational experience as the TrashBot monitor provides relevant information to the user. Each unit can be customized for specific needs through custom AI algorithms based on use type, local recycling requirements, etc. and customized messaging can be programmed into each unit for the end-user. This addresses the challenge of users properly disposing of waste and avoids contamination of waste streams through introduction of improper materials, such as food waste. Lacking proper education about their own recycling efforts, consumers unintentionally contaminate existing recycling streams by discarding recyclables and recyclable containers that contain food waste, especially in public areas where food is purchased and packaged in single-use plastics, such as airports, hospitals, and event venues. Clean Robotics’ technology removes the sorting responsibilities from the consumer at the discard point, using AI, ML, and computer vision to sort, analyze and track the amount and type of recyclables that are being discarded. Removing user intervention improves the quality of the recycling stream with no additional effort from the consumer. This point also provides a captive moment in which consumers can be educated about how to recycle better, based on behaviors identified through that TrashBot’s analytics. Because this information is presented in a novel manner, it is retained by the consumer, improving recycling behaviors at discard points where TrashBots are not in use. Our Phase 1 project, “Automated Waste Sorting at the Point of Disposal,” successfully improved recycling efficiency and reduced carbon emissions on a hospital campus by using AI, computer vision, and robotics to sort waste. TrashBot technology allowed for 300% more accurate sorting than relying on the hospital population to manually sort with conventional trash receptacles. According to Global Market Study, the Global Internet of Bins market is projected to be $25.7B by 2029. A Babson College study estimated the United States waste bin market is $12B Total Addressable Market.
SBIR Phase I:
Automated Waste Sorting at the Point of Disposal | Final ReportThe perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.