Review of Essential Generic Technologies for Visual Perception in Underground Coal Mine Robots

ABSTRACT Visual perception technology serves as the core support for establishing the “perception‐decision‐control” closed‐loop system of underground coal mine robots (UCMRs). Research on its key generic technologies is crucial to promoting the large‐scale deployment of UCMRs in underground mines. This paper initially reviews the development status of UCMRs and elaborates on the functional roles and application scenarios of five core categories: tunneling, coal mining, auxiliary operations, inspection, and rescue robots, thereby clarifying the fundamental requirements of visual perception across diverse underground scenes. Subsequently, it concentrates on the generic technological system essential for UCMR visual perception, presenting an in‐depth analysis of the principles, research advancements, and application challenges related to four technical modules: environmental adaptability under extreme conditions, target detection and recognition in complex scenarios, 3D spatial perception and positioning, and lightweight algorithms suitable for edge computing. Finally, aligned with practical industry needs, the paper projects future development trends and practical challenges, proposing four strategic pathways for breakthroughs, namely human‐machine‐environment integrated active perception, automated iteration of datasets and models, cluster perception and interaction, and cross‐technology integration, and highlighting four core challenges, including environmental adaptability, hardware reliability, communication collaboration, and industry access compatibility. It aims to provide a valuable theoretical reference and technical support for the technological development, achievement transformation, and advancement of mine intellectualization.