风险评估
风险分析(工程)
工程类
风险管理
计算机科学
可靠性工程
系统工程
运输工程
车辆安全
鉴定(生物学)
建筑工程
铁路运输
控制(管理)
风险管理工具
作者
Qi Xia,Peng Chen,Han Li,Sheng Dong,Guoyan Xu,Guizhen Yu
出处
期刊:IEEE Transactions on Vehicular Technology
[Institute of Electrical and Electronics Engineers]
日期:2026-01-01
卷期号:: 1-15
标识
DOI:10.1109/tvt.2026.3738915
摘要
Autonomous driving technology has been extensively deployed in open-pit mining operations, significantly improving operational safety and productivity. However, unlike structured urban roads, open-pit mining areas exhibit inherently unstructured geometries and irregular boundaries, which introduce substantial challenges to the safe operation of Autonomous Mining Truck (AMT). To address safety issues in such scenarios, this paper proposes an integrated risk-field-based framework for multi-source risk assessment and hierarchical risk prevention tailored to open-pit environments. The proposed risk assessment module unifies road risk, obstacle risk, and predictive interaction risk into a normalized quantitative risk metric, which is subsequently provided to a risk prevention module. According to predefined risk levels, the prevention module adaptively generates safe velocity commands or deceleration constraints to suppress further risk escalation. The proposed algorithm is comprehensively validated in a mining-specific simulation platform. Experimental results indicate that, in static scenarios with varying path curvature, the AMT consistently maintains sufficient safety margins from obstacles. In dynamic interaction scenarios, including car-following, crossing, and merging, the framework effectively prevents potential collisions. Moreover, the method demonstrates robustness in abnormal conditions such as path deviation and boundary conflicts. These findings confirm that the proposed approach effectively enhances the operational safety of AMT in open-pit mining environments.
科研通智能强力驱动
Strongly Powered by AbleSci AI