Loading...

Visual Servoing and Control of a Fruit-Sorting Robot Equipped with a Soft Fin Ray Gripper

Adeli, Sara | 2025

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57909 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Sayyaadi, Hassan
  7. Abstract:
  8. The increasing demand for the mechanized harvesting of delicate agricultural products, aimed at reducing dependence on human labor and enhancing productivity, necessitates the development of advanced robotic systems. One of the main challenges in this field is designing robots capable of harvesting fragile products with precision and without causing damage. This study focuses on the design and modeling of a serial robot equipped with an image processing system and a soft gripper inspired by the fish fin effect, intended for harvesting sensitive agricultural products such as tomatoes, strawberries, and plums. Initially, image processing is used to identify and analyze the condition of the agricultural products and their environment. The YOLOv9 deep learning algorithm is employed for the accurate detection and localization of the products, while robot control is managed using a neural network and an adaptive sliding mode controller to enhance the robot's accuracy and performance in dynamic environments. Subsequently, a soft gripper is designed to effectively collect the products without causing damage, utilizing the fish fin ray effect. The gripper’s fingers are optimized to apply appropriate forces when interacting with agricultural products. The theoretical modeling of these grippers is conducted using the FRE method, and its validation is performed through experimental results under real-world conditions. For precise simulation of the gripper's mechanical behavior, the model is also numerically analyzed in ANSYS software, and the results are compared with experimental data. In the next phase, to precisely control the contact force between the gripper and the agricultural products, the same FRE model is applied to design a force controller based on the impedance control method. This controller is designed to automatically adjust the force exerted by the gripper, ensuring the safe harvesting of agricultural products without causing damage. Finally, the performance of the designed system is evaluated through numerical simulations and experimental tests under various conditions. The results demonstrate that the robot is capable of harvesting agricultural products with high precision and efficiency, without inflicting any damage
  9. Keywords:
  10. Adaptive Sliding Control ; Impedance Control ; Adaptive Back-Stepping Sliding Mode ; Fish Fin-Inspired Soft Gripper ; Neural Network-Based Controller ; YOLOv9 Algorithm ; Finite Rigid Elements (FRE)Method ; Agricultural Serial Robot

 Digital Object List

  • محتواي کتاب
  •   view
  •   download

 Bookmark

No TOC