Most autonomous navigation systems used in underground mining vehicles such as load–haul–dump (LHD) vehicles and trucks use 2D light detection and ranging (LIDAR) sensors and 2D representations/maps of the environment. In this article, we propose the use of 3D LIDARs and existing 3D simultaneous localization and mapping (SLAM) jointly with 2D mapping methods to produce or update 2D grid maps of underground tunnels that may have significant elevation changes. Existing mapping methods that only use 2D LIDARs are shown to fail to produce accurate 2D grid maps of the environment. These maps can be used for robust localization and navigation in different mine types (e.g., sublevel stoping, block/panel caving, room and pillar), using only 2D LIDAR sensors. The proposed methodology was tested in the Werra Potash Mine located at Philippsthal, Germany, under real operational conditions. The obtained results show that the enhanced 2D map-building method produces a superior mapping performance compared with a 2D map generated without the use of the 3D LIDAR-based mapping solution. The 2D map generated enables robust 2D localization, which was tested during the operation of an autonomous LHD, performing autonomous navigation and autonomous loading over extended periods of time.

The application of Machine Learning in Mineral Processing and Extractive Metallurgy has important benefits in terms of increasing the predictability and controllability of the processes, optimizing their performance, and improving maintenance. However, this application has significant implementation challenges. This paper analyzes these challenges and proposes ways of addressing them. Among the main identified challenges are data scarcity and the difficulty in characterizing abnormal events/conditions as well as modeling processes, which require the creative use of different learning paradigms as well as incorporating phenomenological models in the data analysis process, which can make the learning process more efficient. Other challenges are related to the need of developing reliable in-line sensors, adopting interoperability data models and tools, and implementing the continuous measurement of critical variables. Finally, the paper stresses the need for training of advanced human capital resources with the required skills to address these challenges.

This work proposes a scheme for learning how to break rocks with an impact hammer. The problem is formulated as a Partially Observable Markov's Decision Process, and then solved through deep reinforcement learning. We propose a simple formulation, requiring only a basic sensorization of the hammer's manipulator, and involving just two discrete actions. We use Dueling Double Deep-Q Networks to parameterize the policy, and wield it with an auxiliary output. The proposed auxiliary task is also trained in simulation, and allows deciding when to stop the operation by detecting the absence of a rock from the observed joints' movement. The resulting policy is tested in a real world experimental environment, using a Bobcat E10 mini-excavator, and various rock types. The results show that a good performance can be obtained in a safe, and robust manner. A video showing some of the obtained results is available in https://youtu.be/tMqDJjK6zPo .

The incorporation of autonomous equipment is fuelling a revolution in mining, but it poses operational challenges due to potential hazardous interactions between humans and the autonomous machinery. For this reason, block and panel caving mines operate under a static confinement policy that stops all autonomous LHDs when workers must enter the production area; thus, having a huge negative impact on productivity. To address this challenge, we propose two dynamic confinement policies, and we model them using discrete event simulation. Results show that the dynamic moderate/intensive policies may lead to increases in production of 35%/45% when compared with the static policy.