Concept and Architecture for Applying Continuous Machine Learning in Multi-Access Routing at Underground Mining Vehicles

Autonomous moving vehicles facilitate mining of ore in underground mines. The vehicles are usually equipped with many sensor-based devices (e.g., Lidar, video camera, proximity sensor, etc.), which enable environmental monitoring, and remote control of the vehicles at the control center. Transfer of...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 12; no. 20; p. 10679
Main Authors Pääkkönen, Pekka, Backman, Jere, Pakkala, Daniel, Paananen, Jori, Seppänen, Kari, Ahola, Kimmo
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.10.2022
Subjects
Architectural elements
Architecture
Autonomous vehicles
Changing environments
continuous learning
Control centres
Decision making
Design
Environmental changes
Environmental monitoring
Learning algorithms
Machine learning
Mining
multi-access networking
Remote control
Remote monitoring
Remote sensors
Research methodology
River
Route planning
Route selection
Underground mines
Underground mining
Vehicles
Wireless communications
Wireless networks
wireless networks access path selection
Online AccessGet full text

Cover

More Information
Summary:Autonomous moving vehicles facilitate mining of ore in underground mines. The vehicles are usually equipped with many sensor-based devices (e.g., Lidar, video camera, proximity sensor, etc.), which enable environmental monitoring, and remote control of the vehicles at the control center. Transfer of sensor-based data from the vehicles towards the control center is challenging due to limited connectivity enabled by the multi-access technologies of the communication infrastructure (e.g., 5G, Wi-Fi) within the underground mine, and the mobility of the vehicles. This paper presents design, development, and evaluation of a concept and architecture enabling continuous machine learning (ML) for optimizing route selection of real-time streaming data in a real and emulated underground mining environment. Continuous ML refers to training and inference based on the most recently available data. Experiments in the emulator indicated that utilization of a ML-based model (based on the RandomForestRegressor) in decision making achieved ~5–13% lower one-way delay in streaming data transfers, when compared to a simpler heuristic model.
ISSN:2076-3417
2076-3417
DOI:10.3390/app122010679