Underground mining environments pose significant challenges for automated hazard detection due to low illumination, restricted visibility, and the absence of Global Navigation Satellite System (GNSS) coverage. These factors limit situational awareness and delay inspection efforts, particularly after disruptive events when rapid assessment is essential for safety. This study addresses this problem by developing a dual-pipeline framework for 2D–3D detection that uses 360° imaging and LiDAR-based machine learning to identify people, vehicles, and positional changes in underground settings without requiring personnel to re-enter hazardous areas. The objective was to create a system capable of recognizing objects and monitoring spatial changes under real underground mine conditions. The 2D component used a Ricoh Theta Z1 camera to collect panoramic images, and a YOLO (You Only Look Once) v8n model was fine-tuned using datasets representing low light, shadowed underground scenes. The 3D component employed an Ouster OS1-070-64 LiDAR sensor, and point clouds were processed through denoising, ICP alignment, surface reconstruction, manual annotation, and 2D projection. A YOLO-based model was then trained to detect objects and measure displacement between LiDAR scans. Results demonstrated strong performance for both components. The fine-tuned YOLOv8n model reliably detected personnel and vehicles despite challenging lighting and visual clutter, while the 3D pipeline localized objects in the registered LiDAR frame and quantified vehicle displacement between consecutive scans by comparing 3D bounding-box centroids after ICP alignment (displacement vector and magnitude). These findings indicate that the combined 2D–3D system can effectively support automated hazard recognition and environmental monitoring in GNSS-denied underground spaces.

While robotic technologies have shown great promise in enhancing productivity and safety, their integration into the mining sector, particularly for search and rescue (SAR) missions, remains limited. The success of these systems depends not only on their technical capabilities, but also on the effectiveness of human–robot interaction (HRI) in high-risk, time-sensitive environments. This review synthesizes key human factors, including cognitive load, situational awareness, trust, and attentional control, that critically influence the design and operation of robotic interfaces for mine rescue missions. Drawing on established cognitive theories such as Endsley’s Situational Awareness Model, Wickens’ Multiple Resource Theory, Mental Model and Cognitive Load Theory, we identified core challenges in current SAR interface design for mine rescue missions and mapped them to actionable design principles. We proposed a human-centered framework tailored to underground mine rescue operations, with specific recommendations for layered feedback, multimodal communication, and adaptive interfaces. By contextualizing cognitive science in the domain of mining emergencies, this work offers a structured guide for designing intuitive, resilient, and operator-supportive robotic systems.