Modernizing Underground Mining Operations with Millimeter-Wave Imaging and Networking

Project Overview

Synopsis: The project aims to address the unique challenges of sensing and networking in underground mining environments by employing millimeter-wave (mmWave) wireless, a core technology for 5G and beyond standards. This technology is particularly suited for the harsh conditions of underground mines, such as dust and low light or dark conditions. However, the adoption of mmWave technology in mining is challenging due to reconstructing high-quality 3D maps in complex structures, fusing static and mobile underground real-time maps, and deploying mmWave communication infrastructures. By overcoming these challenges, this project seeks to enhance safety in mining operations, improve operational efficiency through better resource management, navigation, and machinery positioning, and contribute to the national interest by advancing the future of autonomous mining systems. The collaboration with Indian institutions, known for their mining expertise, funded by the Department of Science and Technology (DST), India, aims to advance the state of the art in modern mining technology. This project supports education and diversity by providing hands-on experiences to students, integrating research results into graduate-level courses, and demonstrating prototypes.

The technical contributions of this project involve three main thrusts. Thrust 1 emphasizes robust 3D mapping with mmWave devices, addressing challenges like motion error and signal sparsity through dynamic velocity estimation and deep learning while integrating mobile and static maps for a comprehensive environment structure. Thrust 2 aims to establish resilient networking alongside mmWave sensing for rapid connectivity and precise mapping, addressing communication systems signaling and latency challenges and leveraging deep learning for efficient mmWave deployment in mines. Thrust 3 presents a comprehensive evaluation plan for validating earlier thrusts through tests with lab-scale prototypes and trials in a mining simulator. Furthermore, the project designs and empirically validates the proposed systems in a mmWave testbed inside a real-world mining environment. This project aligns with global sustainability goals and addresses some of the pressing challenges in the modern mining industry.

Publications and Other Products

  • CoSense: Deep Learning Augmented Sensing for Coexistence with Networking in Millimeter-Wave Picocells
    Zhuangzhuang Gu, Hem Regmi, Sanjib Sur
    TIOT’24 ACM Transactions on Internet of Things, August 2024. [Paper] [Poster]