The shift towards autonomous excavators in construction and mining is a significant leap towards enhancing operational efficiency and ensuring worker safety. However, it presents challenges such as the need for sophisticated decision-making and environmental perception due to complex terrains and diverse conditions. Our study introduces the E-GTN framework, a novel approach tailored for autonomous excavation that leverages advanced multisensor fusion and a custom-designed convolutional neural network to address these challenges. Results demonstrate that GridNet effectively processes grid data, enabling the reinforcement learning algorithm to make informed decisions, thereby ensuring efficient and intelligent autonomous excavator performance. The study concludes that the E-GTN framework offers a robust solution for the challenges in unmanned excavator operations, providing a valuable platform for future advancements in the field.

An algorithm is presented for a micro-model of a mining dump truck movement, which allows determining the optimal speed and acceleration of a vehicle, considering the change of the road grade. The structure of the simulation macro-model of an excavator-and-dump truck complex has been developed. The procedure for integrating a micro-model of a dump truck movement into a simulation model is shown. As a result of a series of experiments with a macro-model, the influence of open pit roads grade on the performance and efficiency of excavator-and-dump truck complexes was established. The necessity of considering in simulation excavator-and-dump truck complexes the speed regulation of dump trucks depending on the change in road grade is shown.

The processing of woody biomass waste piles for use as fuel instead of burning them was investigated. At each landing slash pile location, a 132 kW grapple excavator was used to transfer the waste piles into a 522 kW horizontal grinder. Economies of scale could be expected when grinding a larger pile, although the efficiency of the loading operation might be diminished. Here, three piles were ground and the operations were time-studied: Small (20 m long × 15 m wide × 4 m high), Medium (30 × 24 × 4 m), and Large (35 × 30 × 4 m) piles. Grinding the Medium pile was found to be the most productive at 30.65 bone dry tons per productive machine hour without delay (BDT/PMH₀), thereby suggesting that there might be an optimum size of slash pile for a grinding operation. We also examined modeling of the excavator and grinder operations, and we observed that the constructed simulation model well-replicated the actual operations. Based on the modeling, we estimated that the productivity of grinding at a landing area of 710 m² of slash pile location was 31.24 BDT/PMH₀, which was the most productive rate.