Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards a Thermodynamical Deep-Learning-Vision-Based Flexible Robotic Cell for Circular Healthcare

Federico Zocco, Denis Sleath, Shahin Rahimifard

TL;DR

The paper addresses healthcare material waste by proposing a thermodynamically grounded, vision-enabled robotic cell for disassembly and sorting of small medical devices. It embeds robot dynamics into thermodynamical material networks (TMNs) through a discrete-time mass-flow matrix $\bm{\Gamma}(\mathcal{N}; n)$ and introduces graph-based circularity indicators, linking energy and material flows. Two indicators, the separation rate $r_s$ and separation time $t_s$, quantify how well the cell supports circularity, and are demonstrated via a numerical glucose-meter example. The practical contributions include a flexible robotic cell with deep-learning vision for resources mapping and waste sorting, illustrating how energy–mass considerations can guide the design of recovery chains in healthcare.

Abstract

The dependence on finite reserves of raw materials and the production of waste are two unsolved problems of the traditional linear economy. Healthcare, as a major sector of any nation, is currently facing them. Hence, in this paper, we report theoretical and practical advances of robotic reprocessing of small medical devices. Specifically, on the theory, we combine compartmental dynamical thermodynamics with the mechanics of robots to integrate robotics into a system-level perspective, and then, propose graph-based circularity indicators by leveraging our thermodynamic framework. Our thermodynamic framework is also a step forward in defining the theoretical foundations of circular material flow designs as it improves material flow analysis (MFA) by adding dynamical energy balances to the usual mass balances. On the practice, we report on the on-going design of a flexible robotic cell enabled by deep-learning vision for resources mapping and quantification, disassembly, and waste sorting of small medical devices.

Towards a Thermodynamical Deep-Learning-Vision-Based Flexible Robotic Cell for Circular Healthcare

TL;DR

The paper addresses healthcare material waste by proposing a thermodynamically grounded, vision-enabled robotic cell for disassembly and sorting of small medical devices. It embeds robot dynamics into thermodynamical material networks (TMNs) through a discrete-time mass-flow matrix and introduces graph-based circularity indicators, linking energy and material flows. Two indicators, the separation rate and separation time , quantify how well the cell supports circularity, and are demonstrated via a numerical glucose-meter example. The practical contributions include a flexible robotic cell with deep-learning vision for resources mapping and waste sorting, illustrating how energy–mass considerations can guide the design of recovery chains in healthcare.

Abstract

The dependence on finite reserves of raw materials and the production of waste are two unsolved problems of the traditional linear economy. Healthcare, as a major sector of any nation, is currently facing them. Hence, in this paper, we report theoretical and practical advances of robotic reprocessing of small medical devices. Specifically, on the theory, we combine compartmental dynamical thermodynamics with the mechanics of robots to integrate robotics into a system-level perspective, and then, propose graph-based circularity indicators by leveraging our thermodynamic framework. Our thermodynamic framework is also a step forward in defining the theoretical foundations of circular material flow designs as it improves material flow analysis (MFA) by adding dynamical energy balances to the usual mass balances. On the practice, we report on the on-going design of a flexible robotic cell enabled by deep-learning vision for resources mapping and quantification, disassembly, and waste sorting of small medical devices.
Paper Structure (11 sections, 1 theorem, 42 equations, 4 figures, 1 table)

This paper contains 11 sections, 1 theorem, 42 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Integration of Robotics into a Systemic Framework
  4. Principles of TMNs and Circularity
  5. Robot as a Thermodynamic Compartment
  6. Design of Flexible Robotic Cell
  7. Circularity Indicators of Robotic Cell
  8. Results and Discussion
  9. Current Functionality of Robotic Cell
  10. Numerical Example on Cell Circularity
  11. Conclusions

Key Result

Proposition 1

The standard form of robot dynamics (see Ch. 7 in SicilianoBook) can be derived from the dynamical form of the first principle of thermodynamics where $E$ is the total energy of the robotic manipulator, $\dot{Q}$ is the heat flow exchanged between the manipulator and the surroundings, $\dot{W}$ is the work flow exchanged between the manipulator and the surroundings, $\alpha$ is the number of rig

Figures (4)

  • Figure 1: Main components of the flexible robotic cell.
  • Figure 2: At the top, the mass-flow digraph of the robotic cell. The digraph is applicable to both disassembly and waste sorting scenarios. The red arrows indicate the corresponding time at which the mass leaves or enters a vertex-compartment.
  • Figure 3: Current functionalities of the flexible robotic cell. Inhaler CAD model taken from GrabCAD.
  • Figure 4: Dynamics of the stocks and flows of the robotic cell, which correspond to the entries $\theta_0, \theta_1, \dots, \theta_{10}$ of the mass-flow matrix (\ref{['eq:GammaOfCellExplicit']}).

Theorems & Definitions (7)

  • Definition 1: Discrete-time mass-flow matrix
  • Definition 2: zocco2023thermodynamical
  • Proposition 1
  • proof
  • Remark 1
  • Remark 2
  • Remark 3