Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Vision-Based Robotic Disassembly Combined with Real-Time MFA Data Acquisition

Federico Zocco, Maria Pozzi, Monica Malvezzi

Abstract

Stable and reliable supplies of rare-Earth minerals and critical raw materials (CRMs) are essential for the development of the European Union. Since a large share of these materials enters the Union from outside, a valid option for CRMs supply resilience and security is to recover them from end-of-use products. Hence, in this paper we present the preliminary phases of the development of real-time visual detection of PC desktop components running on edge devices to simultaneously achieve two goals. The first goal is to perform robotic disassembly of PC desktops, where the adaptivity of learning-based vision can enable the processing of items with unpredictable geometry caused by accidental damages. We also discuss the robot end-effectors for different PC components with the object contact points derivable from neural detector bounding boxes. The second goal is to provide in an autonomous, highly-granular, and timely fashion, the data needed to perform material flow analysis (MFA) since, to date, MFA often lacks of the data needed to accurately study material stocks and flows. The second goal is achievable thanks to the recently-proposed synchromaterials, which can generate both local and wide-area (e.g., national) material mass information in a real-time and synchronized fashion.

Vision-Based Robotic Disassembly Combined with Real-Time MFA Data Acquisition

Abstract

Stable and reliable supplies of rare-Earth minerals and critical raw materials (CRMs) are essential for the development of the European Union. Since a large share of these materials enters the Union from outside, a valid option for CRMs supply resilience and security is to recover them from end-of-use products. Hence, in this paper we present the preliminary phases of the development of real-time visual detection of PC desktop components running on edge devices to simultaneously achieve two goals. The first goal is to perform robotic disassembly of PC desktops, where the adaptivity of learning-based vision can enable the processing of items with unpredictable geometry caused by accidental damages. We also discuss the robot end-effectors for different PC components with the object contact points derivable from neural detector bounding boxes. The second goal is to provide in an autonomous, highly-granular, and timely fashion, the data needed to perform material flow analysis (MFA) since, to date, MFA often lacks of the data needed to accurately study material stocks and flows. The second goal is achievable thanks to the recently-proposed synchromaterials, which can generate both local and wide-area (e.g., national) material mass information in a real-time and synchronized fashion.

Paper Structure

This paper contains 6 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Robots for Disassembly and MFA Data
  4. Real-Time at-the-Edge Vision in Robotic Disassembly
  5. Robots for Wide-Area Real-Time Material Monitoring
  6. Conclusion

Figures (3)

  • Figure 1: Annotation of PC desktop components considering different PC models with different end-of-use conditions. Colors of bounding boxes: blue for the motherboard, yellow for the fan, red for the cables, and green for the screws.
  • Figure 2: Bounding boxes generated in real-time by the detectors. The red dots and circles can be computed from the bounding boxes for positioning the grippers and tools needed to extract the PC components.
  • Figure 3: The data for an MFA Sankey diagram mason2025bayesian can be generated via synchromaterials zocco2025synchronized provided by the robots performing assembly, sorting, and disassembly. Computationally-intensive vision systems are justifiable in the case of robotic end-of-use processing (i.e., sorting and disassembly operations) since the geometries of waste items are unknown. Amounts and materials are merely indicative.