Related Experiment Video
Updated: Sep 21, 2025
10:09
Operation of the Collaborative Composite Manufacturing CCM System
Published on: October 1, 2019
6.7K
An Enhanced Positional Error Compensation Method for Rock Drilling Robots Based on LightGBM and RBFN.
Xuanyi Zhou1, Wenyu Bai1,2, Jilin He3
1Key Laboratory of Special Purpose Equipment and Advanced Processing Technology, Zhejiang University of Technology, Hangzhou, China.
Frontiers in Neurorobotics
|June 1, 2022
Summary
This study introduces a hybrid method using Radial Basis Function Networks (RBFN) and Light Gradient Boosting Decision Trees (LightGBM) to improve the precision of rock drilling robots by compensating for diverse errors in tunnel construction.
Area of Science:
- Robotics
- Mechanical Engineering
- Artificial Intelligence
Background:
- Rock drilling robots enhance tunnel construction efficiency and quality but face challenges in high-precision control due to manipulator complexities.
- Diverse and non-linear errors in heavy-load, multi-joint robotic manipulators hinder intelligent control.
Purpose of the Study:
- To propose a hybrid positional error compensation method for rock drilling robots.
- To enhance the control accuracy of robotic manipulators in tunnel construction.
Main Methods:
- Established the manipulator's kinematics model using the Modified Denavit-Hartenberg (MDH) convention.
- Developed a parallel difference algorithm to modify kinematics parameters for geometric error compensation.
- Applied Radial Basis Function Network (RBFN) and Light Gradient Boosting Decision Tree (LightGBM) for non-geometric error analysis and compensation.
Main Results:
- The proposed hybrid method effectively compensates for both geometric and non-geometric errors in rock drilling robots.
- Experimental validation demonstrated the performance enhancement in control accuracy.
Conclusions:
- The hybrid RBFN and LightGBM approach offers a viable solution for improving the precision of rock drilling robots.
- This method addresses the challenges posed by diverse and non-linear errors in complex robotic systems.
