Scenario Engineering for Autonomous Transportation: A New Stage in Open-Pit Mines

TL;DR

Open-pit mining faces harsh environments that challenge autonomous transportation reliability. The paper proposes Scenario Engineering (SE) integrated with autonomous transportation, comprising Scenario Feature Extractor (SFE), Intelligence & Index (I&I), Calibration & Certification (C&C), and Verification & Validation (V&V), underpinned by a Transformer-based SFE and a $6I$/$6S$ data governance framework, plus a federated organizational model. The approach is validated in Baorixile and Haerwusu, showing improved robustness and safety with SEAT, though efficiency remains below manual driving in some cases. The work provides a scalable path to safer, more reliable autonomous mining operations and outlines practical steps for human-centric deployment through foundation-model-enabled services. Overall, SE enables safer, more trustworthy autonomous transportation in open-pit mines and supports broader AI-enabled mining operations.

Abstract

In recent years, open-pit mining has seen significant advancement, the cooperative operation of various specialized machinery substantially enhancing the efficiency of mineral extraction. However, the harsh environment and complex conditions in open-pit mines present substantial challenges for the implementation of autonomous transportation systems. This research introduces a novel paradigm that integrates Scenario Engineering (SE) with autonomous transportation systems to significantly improve the trustworthiness, robustness, and efficiency in open-pit mines by incorporating the four key components of SE, including Scenario Feature Extractor, Intelligence and Index (I&I), Calibration and Certification (C&C), and Verification and Validation (V&V). This paradigm has been validated in two famous open-pit mines, the experiment results demonstrate marked improvements in robustness, trustworthiness, and efficiency. By enhancing the capacity, scalability, and diversity of autonomous transportation, this paradigm fosters the integration of SE and parallel driving and finally propels the achievement of the '6S' objectives.

Figures (7)

• Figure 1: Typical differences between open-pit mining scenarios and urban traffic scenarios.
• Figure 2: The framework of autonomous transportation for open-pit mines, which integrated Scenario Engineering to improve the robustness and trustworthiness of the transportation model. SFE processes all potential input data from the whole scenario perspective, ranging from most multi-source sensor fusion methods used in the perception phase to complex high-level commands employed in the planning phase. I&I is proposed for data argumentation and validation in autonomous transportation in open-pit mines. C&C provides a novel methodology to ensure efficient learning efficiency of the unmanned transportation model as well as the effective criterion of the model’s performance. V&V involves ensuring the correctness and performance of autonomous transportation models at open-pit mines.
• Figure 3: Intelligence & Index for data argumentation and validation in open-pit mines.
• Figure 4: Both visual sensors (e.g. cameras) and non-visual sensors (e.g. LIDAR) are susceptible to processing perturbations. Even the slightest ones can yield an unimaginable influence on computational results, thereby leading to potentially catastrophic incidents in autonomous transportation in open-pit mines.
• Figure 5: ACP-based parallel intelligence framework for autonomous transportation in open-pit mines.