- About Us
- Guidelines
-
The Author ensures that the research has been conducted responsibly and ethically with adherence to all relevant regulations. read more..
- For Authors
- For Reviewer
- Manuscript Guidelines
- Membership
-
- Journals
- Reprints
- e-Books
- Videos
- Indexing
- Contact Us
COVID-19
- Submissions
Abstract
Aspects in Mining & Mineral Science
Investigation of Tool-Soil Interaction and Autonomous Front-Loader Motion Planning
-
Open or CloseLihi Kalakuda* and Amir Shapiro
Department of Mechanical Engineering, Ben Gurion University, Israel
*Corresponding author: Lihi Kalakuda, Department of Mechanical Engineering, Ben Gurion University, Israel
Submission: September 28, 2020; Published: October 22, 2020
ISSN : 2578-0255Volume5 Issue5
Abstract
The world still relies on human labor when it comes to operating heavy machinery. This dependence on human labor is expensive, time-intensive, and hazardous. This paper deals with an autonomous front- loader movement planning for a soil loading task. We used reinforcement learning algorithm trained by a Gazebo simulator integrated with ROS and OpenAI Gym framework. The continuum model was chosen as the soil-tool interaction model. Next, we trained outrobot to load soil utilizing Proximal Policy Optimization algorithms. Our results show that this algorithm yields high return with a moderate number of training steps.
Keywords:Autonomous; Material; Bucket filling; Soil-tool; Loader; Hydraulics
Editor In Chief
.jpg)
Signup for Newsletter
Quick Links
Editorial Board Registrations
Submit your Article
Best Paper of the Volume
Reprints
Refer a Friend
Advertise With UsOur Recent Edition
.jpg)
Top Editors
.jpg)
.bmp)
.jpg)
.png)
.jpg)
.png)
.png)
.png)
Financial Support
Sponsors
Latest e-Books
Latest Video
a Creative Commons Attribution 4.0 International License. Based on a work at www.crimsonpublishers.com.
Best viewed in 
| Above IE 9.0 version