Schlosser A, Nemoto T, Walter J, Amon S, Franke J, Reitelshofer S (2025)
Publication Type: Conference contribution
Publication year: 2025
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 2824-2835
Conference Proceedings Title: Proceedings - Winter Simulation Conference
Event location: Seattle, WA, USA
ISBN: 9798331587260
DOI: 10.1109/WSC68292.2025.11339084
Post-consumer packaging waste continues to rise, intensifying the need for automated sorting to increase recycling efficiency. Lightweight packaging (LWP), with its variable geometries, materials, and occlusions, remains especially difficult for conventional vision systems. Integrating You Only Look Once (YOLO) instance segmentation into robotic simulation platforms enables robust real-time detection. Experiments show that synthetic datasets yield consistently high segmentation accuracy, whereas real-world performance fluctuates. Crucially, increasing model size or resolution does not guarantee improvement; task-specific tuning and system-level integration are more effective. Simulation frameworks combining Unity, Robot Operating System 2 (ROS2), and MoveIt2 provide realistic evaluation and optimization. These findings demonstrate that AI-based segmentation and digital twins can deliver scalable, adaptive, and self-optimizing sorting systems, offering a practical pathway to sustainable material recovery and circular economy implementation.
APA:
Schlosser, A., Nemoto, T., Walter, J., Amon, S., Franke, J., & Reitelshofer, S. (2025). Automated Detection in Unstructured Material Streams: Challenges and Solutions. In Proceedings - Winter Simulation Conference (pp. 2824-2835). Seattle, WA, USA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Schlosser, Alexander, et al. "Automated Detection in Unstructured Material Streams: Challenges and Solutions." Proceedings of the 2025 Winter Simulation Conference, WSC 2025, Seattle, WA, USA Institute of Electrical and Electronics Engineers Inc., 2025. 2824-2835.
BibTeX: Download