Loading...
Soft robot workspace estimation via finite element analysis and machine learning
Ambaye, Getachew
Ambaye, Getachew
Citations
Altmetric:
Files
Loading...
Ambaye_2025.pdf
Adobe PDF, 23.15 KB
Authors
Other Names
Location
Time Period
Original Date
Digitization Date
Issue Date
2025-04-11
Type
Abstract
Genre
Keywords
Subjects (LCSH)
Citation
Ambaye, G. 2025. Soft robot workspace estimation via finite element analysis and machine learning. -- In Proceedings: 21st Annual Symposium on Graduate Research and Scholarly Projects. Wichita, KS: Wichita State University
Abstract
Soft robots are robots with flexible bodies, which make them safer for working with humans and adaptable to changing environments. But controlling them can be tricky because their movements are complicated. This study examines the motion of a pneumatic soft robot, which uses air pressure to generate movement, through a combination of Finite Element Analysis (FEA) and machine learning techniques. The robot consists of two parallel, hyper-elastic chamber tubes that expand and bend in response to pressure, mimicking the movement of an elephant’s trunk. One chamber spans the full length of the robot, while the second chamber is half the length, providing asymmetry that allows for more flexible and varied motion. The goal is to use machine learning to develop a predictive model that links the pressure input to the robot’s movement, which is a key challenge in controlling soft robots. By training an artificial neural network (ANN) on the simulation data from FEA, we created a model that can accurately estimate the robot's movement, achieving an impressive R-squared value of 0.99 and a low root mean square error of 0.783. Additionally, we compared the capabilities of robots with different designs: the two-chamber robot can reach a workspace approximately 185 times larger than a single-chamber robot. This approach blends engineering, machine learning, and design to address the challenges of soft robot control, offering insights into their potential applications in real-world environments.
Table of Contents
Description
Presented to the 21st Annual Symposium on Graduate Research and Scholarly Projects (GRASP) held at the Rhatigan Student Center, Wichita State University, April 11, 2025.
Research completed in the Department of Industrial, Systems, and Manufacturing Engineering, College of Engineering.
Research completed in the Department of Industrial, Systems, and Manufacturing Engineering, College of Engineering.
Publisher
Wichita State University
Journal
Book Title
Series
GRASP
v. 21
v. 21