Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Unification Between Deep-Learning Vision, Compartmental Dynamical Thermodynamics, and Robotic Manipulation for a Circular Economy

Federico Zocco, Wassim M. Haddad, Andrea Corti, Monica Malvezzi

TL;DR

This paper merging deep-learning vision, compartmental dynamical thermodynamics, and robotic manipulation into a theoretically-coherent physics-based research framework to lay the foundations of circular flow designs of materials and discusses the still not fully exploited opportunities for robotics in circular economy.

Abstract

The shift from a linear to a circular economy has the potential to simultaneously reduce uncertainties of material supplies and waste generation. However, to date, the development of robotic and, more generally, autonomous systems have been rarely integrated into circular economy implementation strategies despite their potential to reduce the operational costs and the contamination risks from handling waste. In addition, the science of circularity still lacks the physical foundations needed to improve the accuracy and the repeatability of the models. Hence, in this paper, we merge deep-learning vision, compartmental dynamical thermodynamics, and robotic manipulation into a theoretically-coherent physics-based research framework to lay the foundations of circular flow designs of materials. The proposed framework tackles circularity by generalizing the design approach of the Rankine cycle enhanced with dynamical systems theory. This differs from state-of-the-art approaches to circular economy, which are mainly based on data analysis, e.g., material flow analysis (MFA). We begin by reviewing the literature of the three abovementioned research areas, then we introduce the proposed unified framework and we report the initial application of the framework to plastics systems along with initial simulation results of reinforcement-learning control of robotic waste sorting. This shows the framework applicability, generality, scalability, and the similarity and difference between the optimization of artificial neural systems and the proposed compartmental networks. Finally, we discuss the still not fully exploited opportunities for robotics in circular economy and the future challenges in the theory and practice of the proposed circularity framework.

A Unification Between Deep-Learning Vision, Compartmental Dynamical Thermodynamics, and Robotic Manipulation for a Circular Economy

TL;DR

This paper merging deep-learning vision, compartmental dynamical thermodynamics, and robotic manipulation into a theoretically-coherent physics-based research framework to lay the foundations of circular flow designs of materials and discusses the still not fully exploited opportunities for robotics in circular economy.

Abstract

The shift from a linear to a circular economy has the potential to simultaneously reduce uncertainties of material supplies and waste generation. However, to date, the development of robotic and, more generally, autonomous systems have been rarely integrated into circular economy implementation strategies despite their potential to reduce the operational costs and the contamination risks from handling waste. In addition, the science of circularity still lacks the physical foundations needed to improve the accuracy and the repeatability of the models. Hence, in this paper, we merge deep-learning vision, compartmental dynamical thermodynamics, and robotic manipulation into a theoretically-coherent physics-based research framework to lay the foundations of circular flow designs of materials. The proposed framework tackles circularity by generalizing the design approach of the Rankine cycle enhanced with dynamical systems theory. This differs from state-of-the-art approaches to circular economy, which are mainly based on data analysis, e.g., material flow analysis (MFA). We begin by reviewing the literature of the three abovementioned research areas, then we introduce the proposed unified framework and we report the initial application of the framework to plastics systems along with initial simulation results of reinforcement-learning control of robotic waste sorting. This shows the framework applicability, generality, scalability, and the similarity and difference between the optimization of artificial neural systems and the proposed compartmental networks. Finally, we discuss the still not fully exploited opportunities for robotics in circular economy and the future challenges in the theory and practice of the proposed circularity framework.
Paper Structure (13 sections, 3 equations, 2 figures, 1 table)

This paper contains 13 sections, 3 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. THREE REPRESENTATIVE TOPICS FOR CIRCULAR ECONOMY
  3. Circular Economy
  4. Compartmental Dynamical Thermodynamics
  5. Robotic Manipulation for Reprocessing
  6. Deep-Learning Vision for Robotics
  7. UNIFICATION OF DEEP-LEARNING VISION, COMPARTMENTAL THERMODYNAMICS, ROBOTIC MANIPULATION, AND CIRCULAR ECONOMY
  8. A BIBLIOTHECA OF COMPARTMENTS
  9. OPPORTUNITIES FOR ROBOTICS IN CIRCULAR ECONOMY
  10. Framework Application to a Case Study and Challenges
  11. Initial Application to Plastics Systems
  12. Limitations and Challenges
  13. CONCLUSION

Figures (2)

  • Figure 1: Systemic view for deep-learning vision, compartmental dynamical thermodynamics, and robotic manipulation coherently combined to design circular flows of materials. Nomenclature adopted from Zocco et al.zocco2023thermodynamical.
  • Figure 2: Initial application of the proposed framework to design plastic and bio-plastic flows. The framework is a generalization of the Rankine cycle (Fig. \ref{['fig:RankineAsTMN']}), where the working fluid is designed to be circular. At this initial stage, we focus on the sorting and the disassembly compartments performed via robotic manipulators controlled with deep RL (compartments in yellow).

Theorems & Definitions (1)

  • Remark