ROBOCYCLE: Autonomous Dual-Arm Robotic Manipulation and Coordination for Recycling Applications
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Instance SegmentationPoint CloudsSimilar Papers 제목 키워드 기반
RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demo…
Code GenerationPrecise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
Reinforcement learning (RL) holds great promise for enabling autonomous acquisition of complex robotic manipulation skills, but realizing this potential in real-world settings has been challenging. We present a human-in-…
Imitation LearningReinforcement Learning (RL)RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)
In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demo…
Code GenerationBiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination
Bimanual manipulation, i.e., the coordinated use of two robotic arms to complete tasks, is essential for achieving human-level dexterity in robotics. Recent simulation benchmarks, e.g., RoboTwin and RLBench2, have advanc…
CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks
Multi-Agent Reinforcement Learning (MARL) provides a powerful framework for learning coordination in multi-agent systems. However, applying MARL to robotics remains challenging due to their high-dimensional continuous jo…
Multi-agent Reinforcement Learning