Our project’s goal is to help innovate material recovery facilities’ sorting methods required to separate materials before they can be recycled. We designed an autonomous system which is capable of detecting and removing recycled materials from a conveyor belt through the use of deep learning object localization and classification as well as a bi-directional arm with pneumatic suction cups. We also created our own dataset to train our deep learning model and a user interface to correct it during operation. Through these methods we seek to further refine and optimize the way places like Massachusetts sort their waste.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Wach, Lauren
• Bargman, Nathan
• Tulig, Conrad
• Fichtner, Kaitlyn
• Ruping, Garett
• Marquette, Mary

Subject

• Industry
• Well-Being
• Innovation
• Environment
• Sustainability

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-042722-125500
• 64306

Parola chiave

• Object Detection
• Waste Sorting
• Environmental Robotics
• Human Robot Interaction
• Deep Learning
• Recycling

Advisor

• Rudolph, Jennifer
• Calli, Berk
• Wodin-Schwartz, Sarah Jane

Year

• 2022

UN Sustainable Development Goals

• 3 - Good Health and Well-being
• 8 - Decent Work and Economic Growth
• 9 - Industry, Innovation and Infrastructure
• 11 - Sustainable Cities and Communities
• 13 - Climate Action

Date created

• 2022-04-27

Resource type

• Major Qualifying Project

Major

• Computer Science
• Robotics Engineering

Rights statement

• In Copyright