Gravel is the most frequently used material in infrastructure construction. However, the irregular shape of the gravel pile makes it challenging for the loader to predict a stable shoveling position, which can easily result in partial collapse or a complete landslide, thereby posing a serious threat to the equipment. In view of the imperfect method of determining the shoveling position of the pile by the current unmanned loader and the high hardware requirements for the deployment of the identification model, this paper first establishes a mathematical model of the loader, and preliminarily determines the influence of the concave and convex edges of the gravel pile on the shoveling position selection through discrete element joint simulation; secondly, the influence of the pile with different edge curvatures on the loader operation process is analyzed in the simulation software, and the radar map is used to further identify the superior position features; finally, Ghost Net is used as the backbone network, the RFB module is introduced into the Backbone, and the CBAM attention mechanism is integrated into the C3 module to identify the lightweight YOLOv5s shoveling position. Discrete element analysis and a lightweight network model were used in the above study to find the safest and most effective shoveling positions. During the test that mimicked how the loader would actually shovel, the number of parameters in the improved model was cut down to 32.5% of the original, the number of calculations was cut down to about 55.2% of the original, and the average accuracy of finding the shoveling position of the gravel pile reached 98%.
As mining technology advances, intelligent robots in open-pit mining require precise localization and digital maps. Nonetheless, significant pitch variations, uneven highways, and rocky surfaces with minimal texture present substantial challenges to the precision of feature extraction and positioning in traditional visual SLAM systems, owing to the intricate terrain features of open-pit mines. This study proposes an improved SLAM technique that integrates visual and Inertial Measurement Unit (IMU) data to address these challenges. The method incorporates a point–line feature fusion matching strategy to enhance the quality and stability of line feature extraction. It integrates an enhanced Line Segment Detection (LSD) algorithm with short segment culling and approximate line merging techniques. The combination of IMU pre-integration and visual feature restrictions is executed inside a tightly coupled visual–inertial framework utilizing a sliding window approach for back-end optimization, enhancing system robustness and precision. Experimental results demonstrate that the suggested method improves RMSE accuracy by 36.62% and 26.88% on the MH and VR sequences of the EuRoC dataset, respectively, compared to ORB-SLAM3. The improved SLAM system significantly reduces trajectory drift in the simulated open-pit mining tests, improving localization accuracy by 40.62% and 61.32%. The results indicate that the proposed method demonstrates significance.