Search

Open-pit mines, characterized by complicated environmental conditions and unstructured roads, pose challenges for the path planning of mine trucks, marked by inefficiency due to long-distance search and the need to adhere to the left-hand traffic rules common in mining settings. This paper introduces an optimization algorithm for adaptive dual-layer search path planning based on the left-hand traffic rules in mining areas, aiming to improve the navigation performance of mine trucks within these areas while ensuring the path safety and the real-time planning. The upper-layer search, employing the rapidly-exploring random tree (RRT) algorithm and accommodating the environmental characteristics of mining areas, features adaptive adjustments of search step sizes, achieving efficient searches with larger step sizes in open areas, while detailed searches with smaller step sizes in narrow or winding areas. Moreover, the search process is further optimized by setting range constraints for left-hand driving, to prevent potential vehicle conflicts and facilitate rapid convergence of path search. The lower-layer search incorporates a hybrid A* algorithm, effectively narrowing search space and enhancing the real-time nature of path planning through a reward and penalty mechanism for path selection. Furthermore, Reeds-Shepp (RS) curve and an improved cubic spline curve are applied to smooth the resultant path, not only optimizing path curvature but also ensuring that the mine truck reaches the target location in an optimal posture. Further optimization through the gradient descent method enables the efficient generation of safe and smooth paths. Experimental results showed a 14.8% reduction in path generation time and a 0.011 m-1 decrease in path curvature, demonstrating a significant enhancement in the navigation efficiency and safety during autonomous truck driving in mining areas.

At present, the research on unmanned mine truck system on-board decision system in mine scenarios at home and abroad is still in the initial stage, and its research focus is mainly on global planning and scheduling to improve overall safety and efficiency of the system, while ignoring the research on the mine truck independent decision method based on the global planning and scheduling. In order to further improve the safety and efficiency of the system, this paper focuses on the two core functions of behavior decision-making and motion planning under the mining truck independent decision-making method of the vehicle decision-making system. Behavior decision includes driving mode and task mode decision, collision warning and protection decision, fault classification and safety oriented decision, based on the double layer limited state machine method to realize mine truck autonomous decision protection judgment, to ensure that the vehicle in the "loading, transportation, unloading" whole process scenario of mine to improve the safety of vehicle operation. Motion planning includes speed planning and path planning. This paper adopts the quadratic programming algorithm based on the shortest time and the optimal energy consumption to solve the speed planning, and adopts the hybrid A-star and curve fitting algorithm based on special scenarios to solve the local path planning, so that the operation efficiency can be improved by 10%~20% in the loading and unloading parking scenario. The system has been production and operation in a mining area in northern China for half a year. The real vehicle production and operation results show that the system can effectively improve the vehicle operation efficiency and safety ability to avoid obstacles.

In order to improve the adaptability of hybrid A* algorithm to mining scene, this paper proposes a path optimization method for unmanned mine trucks. Firstly, applicability and curvature continuity of initial solution of hybrid A* algorithm are improved by curvature continuous Reeds-Shepp screening in combination with mining scenes, and then the segmented spline curve numerical optimization method based on quadratic programming is used to further smooth and interpolate the searched path. This method can be applied to the screening and smooth optimization of the initial solution of path planning, and provides a safe, smooth and drivable path for unmanned mine trucks that satisfies the kinematic constraints of the vehicle. The results of simulation comparison test and on site vehicle test show that the proposed method can significantly improve the applicability and smoothness of the search path by the traditional hybrid A* algorithm, and the optimization efficiency is better than the traditional discrete point optimization.

With the deep exploration of large open-pit coal mines, the phenomenon of steep slopes and many bends has gradually increased. Moreover, the mine-used truck driving is difficult and there are hidden safety hazards. Therefore, a design scheme of unmanned driving system for open-pit coal mine trucks is proposed. The unmanned driving system includes a vehicular autonomous package, a vehicle-to-ground wireless data communication system and a ground management system. The driving system can realize the completely unmanned autonomous operation of ‘loading, transporting and unloading’ of mine-used trucks. In order to meet the demand of unstructured environment sensing in open-pit coal mines, a multi-source heterogeneous sensor fusion sensing algorithm for the unstructured environment of open-pit coal mines is proposed. According to the driving demand of mine-used trucks in different load qualities and different slopes, a longitudinal adaptive control algorithm considering the quality and slope is proposed to meet the requirements of longitudinal speed control and distance control under the working conditions of slope stop, slope start, fixed-point stop and shovel stop with different load qualities of mine-used trucks. According to the driving demand of large curvature steering and reversing in the mining area, the forward and backward lateral control methods based on variable parameter adaption are proposed to meet the requirements of lateral precise control of all complex roads in the mining area. The unmanned driving system has been tested in different environments such as muddy roads and night environments in the Harwusu Open-pit Coal Mine. The results show that the unmanned driving system has the ability to operate in the mining area, can track accurately, avoid obstacles and perform tasks autonomously. The ground control system can control the start and shutdown of unmanned mine-used trucks, and can remotely control and drive the mine-used trucks if necessary. The various functions of the system are stable and reliable. The development trend of unmanned driving systems in mines is pointed out. ① For vehicular system, it is necessary to build systematic and product-oriented thinking at first, select the corresponding hardware in the form of products, and improve the adaptability of the hardware in the mining area. The perception system should focus on improving the target recognition ability in the complex and heavy dust environment so as to improve the detection redundancy. The control system should focus on improving the response speed of the wire-controlled actuator so as to improve the accuracy of the load quality acquisition. The decision-making system should focus on the guiding safety at first, and further consider the guiding efficiency and improve the system operation efficiency. ② For the ground system, it should fully integrate the existing achievements of the previous stage of digital mine and be compatible with the current mining area scheduling management system. It should focus on the development of mixed running and multi-vehicle cooperative management system, which has the efficiency and energy-saving control indexes in multi-vehicle scheduling. It is proposed that the ‘cloud control’ technology should be developed vigorously, and V2X (Vehicle-to-Everything) and other advanced methods should be used to improve the cooperative safety of unmanned driving systems.

To tackle the challenges posed by dense small objects and fuzzy boundaries on unstructured roads in the mining scenario, we proposed an end-to-end small object detection and drivable area segmentation framework for open-pit mining. We employed a convolutional network backbone as a feature extractor for both two tasks, as multi-task learning yielded promising results in autonomous driving perception. To address small object detection, we introduced a lightweight attention module that allowed our network to focus more on the spatial and channel dimensions of small objects without impeding inference time. We also used a convolutional block attention module in the drivable area segmentation subnetwork, which assigned more weight to road boundaries to improve feature mapping capabilities. Furthermore, to improve our network perception accuracy of both tasks, we used weighted summation when designing the loss function. We validated the effectiveness of our approach by testing it on pre-collected mining data which were called Minescape. Our detection results on the Minescape dataset showed 87.8% mAP index, which was 9.3% higher than state-of-the-art algorithms. Our segmentation results surpassed the comparison algorithm by 1 percent in MIoU index. Our experimental results demonstrated that our approach achieves competitive performance. [ABSTRACT FROM AUTHOR]