AI for ERW Detection in Clearance Operations - The State of Research

2024-10-31

arXiv.org

AI Summary

Current detection and clearance of explosive remnants of war (ERW) remain heavily manual, posing severe safety risks and operational inefficiencies; AI applications are fragmented and lack systematic synthesis. Method: This paper introduces the first dual-track research map for AI-enabled ERW operations, systematically reviewing 2010–2023 literature using integrated methodologies—including traditional machine learning, computer vision, multimodal data fusion, and geospatial analysis. Contribution/Results: We identify two dominant technical paradigms—object detection and risk prediction—and reveal a critical lag in the latter. We propose three novel research directions: “risk prediction revitalization,” “multisource AI fusion,” and “pattern-driven prediction,” emphasizing dynamic integration of domain expertise and human-AI collaborative workflows. This work establishes the most comprehensive academic map of AI+ERW to date, precisely pinpointing key research gaps and delivering an actionable, translation-oriented roadmap for humanitarian demining practice. (149 words)

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The clearance of explosive remnants of war (ERW) continues to be a predominantly manual and high-risk process that can benefit from advances in technology to improve its efficiency and effectiveness. In particular, research on artificial intelligence for ERW clearance has grown significantly in recent years. However, this research spans a wide range of fields, making it difficult to gain a comprehensive understanding of current trends and developments. Therefore, this article provides a literature review of academic research on AI for ERW detection for clearance operations. It finds that research can be grouped into two main streams, AI for ERW object detection and AI for ERW risk prediction, with the latter being much less studied than the former. From the analysis of the eligible literature, we develop three opportunities for future research, including a call for renewed efforts in the use of AI for ERW risk prediction, the combination of different AI systems and data sources, and novel approaches to improve ERW risk prediction performance, such as pattern-based prediction. Finally, we provide a perspective on the future of AI for ERW clearance. We emphasize the role of traditional machine learning for this task, the need to dynamically incorporate expert knowledge into the models, and the importance of effectively integrating AI systems with real-world operations.

Problem

• AI for detecting explosive ordnance in clearance operations
• Improving efficiency and effectiveness of manual EO detection
• Addressing gaps in AI research for EO risk prediction

Innovation

• AI for EO object detection
• AI for EO risk prediction
• Combine AI systems and data