ROBOCYCLE: Autonomous Dual-Arm Robotic Manipulation and Coordination for Recycling Applications

2026-07-03

AI Summary

This work addresses the challenge of automating urban waste sorting by tackling the limitations of current robotic systems in perceiving and manipulating transparent, deformable, or cluttered waste items. The authors propose a dual-arm autonomous sorting system tailored to Tokyo’s recycling standards, integrating a novel dual-arm coordination mechanism, multi-view RGB-D instance segmentation based on RF-DETR, and six-degree-of-freedom grasp planning via AnyGrasp. This integrated approach enables robust manipulation of irregular and deformable objects and supports fine-grained tasks such as unscrewing PET bottle caps. Evaluated in real-world conditions, the system achieves a 90.3% grasp success rate and an overall task success rate of 84.3%, offering a scalable solution for automated waste management in complex human environments.

Abstract

As urban waste volumes escalate and labor shortages intensify, automated waste sorting systems are becoming a necessity. However, current robotic solutions often struggle with the 3D perception and manipulation of transparent, deformable, or cluttered objects. This work introduces ROBOCYCLE, an autonomous dual-arm robotic recycling platform designed to meet the recycling standards of the Tokyo metropolitan area. Our approach integrates multi-view RGB-D perception, transformer-based instance segmentation using RF-DETR, and 6-DoF grasp planning via the Anygrasp SDK. By processing segmentated point clouds, the system generates robust candidate poses for irregular and deformable waste. The system achieved a 90.3% grasp success rate and 84.3% overall task success rate, effectively performing complex coordinated tasks such as unscrewing PET bottle caps. The proposed platform offers a scalable solution for autonomous waste management in real-world human environments.

Problem

• waste sorting
• 3D perception
• deformable objects
• transparent objects
• robotic manipulation

Innovation

• dual-arm robotic manipulation
• transformer-based instance segmentation
• 6-DoF grasp planning
• RGB-D perception
• autonomous recycling