Aiming at the problem of how to enable the mobile robot to navigate and traverse efficiently and safely in the unknown indoor environment and map the environment, an eight-direction scanning detection (eDSD) algorithm is proposed as a new pathfinding algorithm. Firstly, we use a laser-based SLAM (Simultaneous Localization and Mapping) algorithm to perform simultaneous localization and mapping to acquire the environment information around the robot. Then, according to the proposed algorithm, the 8 certain areas around the 8 directions which are developed from the robot’s center point are analyzed in order to calculate the probabilistic path vector of each area. Considering the requirements of efficient traverse and obstacle avoidance in practical applications, the proposal can find the optimal local path in a short time. In addition to local pathfinding, the global pathfinding is also introduced for unknown environments of large-scale and complex structures to reduce the repeated traverse. The field experiments in three typical indoor environments demonstrate that deviation of the planned path from the ideal path can be kept to a low level in terms of the path length and total time consumption. It is confirmed that the proposed algorithm is highly adaptable and practical in various indoor environments.

The life cycle of mining results in various patterns of surface deformation as it progresses through development, production, and reclamation. Therefore, the spatial–temporal patterns of ground deformation provide a crucial indicator to understand the mining activities, related geohazards, and environmental restoration. This study investigates the decadal deformation (2012–2022) of three coal mines during different stages of mines’ life cycles in Henan, China, using radar interferometry with Radarsat-2 and Sentinel-1 data. The results reveal multiple deformation patterns across different areas: the Changcun mine area changed from ground subsidence to uplift following the termination of exploitation in 2016; the Xiadian mine area has been continuously developing over the past decade, resulting in a cumulative subsidence of 55.6 mm; and the Liyuan mine area exhibits surface rebound at a rate of 7.9 mm/year since its closure in 2007. We also probe the mining geometry of the production process by using a rectangular model. This study highlights the significance of long-term InSAR observations and deformation modeling in elucidating the mining operation dynamics of small mining zones in their production, transition, and post-closure periods, thereby facilitating the management of small-scale mining.

Landslide event warning in mining areas is essential for geohazard risk mitigation and infrastructure safety. With the increasing use of Global Navigation Satellite System (GNSS) monitoring networks, warning decisions are often derived from abnormal deformation responses in continuous displacement records. However, deriving stable and transferable warning decisions from GNSS networks is challenged by spatially coupled station responses, time-varying displacement patterns, and incomplete or disturbed observations. To address these issues, this study proposes a graph-augmented gradient boosting decision tree framework, termed GA-GBDT (Graph-Augmented Gradient Boosting Decision Trees), for multi-station landslide event warning in mining areas. The framework first constructs a weighted station graph to encode spatial dependence across stations. Based on this graph, a Gated Recurrent Unit (GRU) and a Graph Convolutional Network (GCN) are integrated to learn spatio-temporal embeddings, which are then fused with station-wise features and fed into XGBoost (eXtreme Gradient Boosting) for warning decision-making. Experiments on a 90-station GNSS network show that GA-GBDT outperforms representative rule-based, machine-learning, and deep-learning baselines, achieving more robust warning performance with improved generalization and false-alarm control. These results indicate that GA-GBDT improves warning robustness, decision stability, and cross-zone generalization for GNSS-based landslide warning in mining areas, with potential transferability to other slope warning scenarios.