Nattapat Koomklang¹, Prem Gamolped¹, Eiji Hayashi¹, Abbe Mowshowitz^2
1Department of Mechanical Information Science and Technology, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, Japan
²Department of Computer Science, The City College of New York, 160 Convent Avenue, New York, NY 10031, USA
pp. 33–38
ABSTRACT
This research paper presents a novel approach for accurate weight estimation in robotic manipulation of noodle-like objects. The proposed approach combines vision transformer and autoencoder techniques with action data and RGB-D encoding to enhance the capabilities of robots in manipulating objects with varying weights. A deep-learning neural network is introduced to estimate the grasping action of a robot for picking up noodle-like objects using RGB-D camera input, a 6-finger gripper, and Cartesian movement. The hardware setup and characteristics of the noodle-like objects are described. The study builds upon previous work in RGB-D perception, weight estimation, and deep learning, addressing the limitations of existing methods by incorporating robot actions. The effectiveness of vision transformers, autoencoders, self-supervised deep reinforcement learning, and deep residual learning in robotic manipulation is discussed. The proposed approach leverages the Transformer network to encode sequential and spatial information for weight estimation. Experimental evaluation on a dataset of 20,000 samples collected from real environments demonstrates the effectiveness and accuracy of the proposed approach in grappling noodle-like objects. This research contributes to advancements in robotic manipulation, enabling robots to manipulate objects with varying weights in real-world scenarios.

ARTICLE INFO
Article History
Received 02 December 2022
Accepted 17 August 2023

Keywords
Robotic manipulation
Weight estimation
Noodle-like objects
Vision transformer
Autoencoder
RGB-D encoding
Deep learning
Transformer network

JRNAL10105

Download article(PDF)