Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Vision-based Manipulation of Transparent Plastic Bags in Industrial Setups

F. Adetunji, A. Karukayil, P. Samant, S. Shabana, F. Varghese, U. Upadhyay, R. A. Yadav, A. Partridge, E. Pendleton, R. Plant, Y. Petillot, M. Koskinopoulou

TL;DR

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm by employing advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs).

Abstract

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm. Industry 4.0, driven by data, connectivity, analytics, and robotics, promises enhanced accessibility and sustainability throughout the value chain. The integration of autonomous systems, including collaborative robots (cobots), into industrial processes is pivotal for efficiency and safety. The proposed solution employs advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs), to identify transparent plastic bags under varying lighting and background conditions. Tracking algorithms and depth sensing technologies are utilized for 3D spatial awareness during pick and placement. The system addresses challenges in grasping and manipulation, considering optimal points, compliance control with vacuum gripping technology, and real-time automation for safe interaction in dynamic environments. The system's successful testing and validation in the lab with the FRANKA robot arm, showcases its potential for widespread industrial applications, while demonstrating effectiveness in automating the unpacking and cutting of transparent plastic bags for an 8-stack bulk-loader based on specific requirements and rigorous testing.

Vision-based Manipulation of Transparent Plastic Bags in Industrial Setups

TL;DR

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm by employing advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs).

Abstract

This paper addresses the challenges of vision-based manipulation for autonomous cutting and unpacking of transparent plastic bags in industrial setups, aligning with the Industry 4.0 paradigm. Industry 4.0, driven by data, connectivity, analytics, and robotics, promises enhanced accessibility and sustainability throughout the value chain. The integration of autonomous systems, including collaborative robots (cobots), into industrial processes is pivotal for efficiency and safety. The proposed solution employs advanced Machine Learning algorithms, particularly Convolutional Neural Networks (CNNs), to identify transparent plastic bags under varying lighting and background conditions. Tracking algorithms and depth sensing technologies are utilized for 3D spatial awareness during pick and placement. The system addresses challenges in grasping and manipulation, considering optimal points, compliance control with vacuum gripping technology, and real-time automation for safe interaction in dynamic environments. The system's successful testing and validation in the lab with the FRANKA robot arm, showcases its potential for widespread industrial applications, while demonstrating effectiveness in automating the unpacking and cutting of transparent plastic bags for an 8-stack bulk-loader based on specific requirements and rigorous testing.

Paper Structure

This paper contains 9 sections, 3 equations, 7 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. MECHANICAL DESIGN
  3. DEEP-LEARNING-BASED OBJECT DETECTION AND MANIPULATION
  4. QR Code Based Depth Estimation and Tracking
  5. Data Acquisition
  6. Robot control for pick-n-place of detected plastic bags
  7. AUTONOMOUS CUTTING & CONTROL
  8. EXPERIMENTAL RESULTS
  9. DISCUSSION & CONCLUSIONS

Figures (7)

  • Figure 1: a. CAD model of the vision-based gripping system; b. real system embedded in the Franka robot.
  • Figure 2: CAD model designs of the system's components: a. eight-stack design assembly; b. delivery system; c. pushing mechanism; d. bottom suction mechanism; e. cutting mechanism.
  • Figure 3: Plastic-container stack detection process. (a) Zone identification and QR-code detection of zone 1, along with its center co-ordinates; (b) First zone stack detection and tracking of the next picking target (marked with the green dot); (c) plastic-container stack detection of zone 2.
  • Figure 4: YOLO_V5 training process: Original is the captured image; Converted is the grayscale image; Labelled is the ground truth; and the last one is the result after detection.
  • Figure 5: Robotic manipulation workflow.
  • ...and 2 more figures