2023· International Journal of Modern Research in Science & Engineering· 0 citations
TL;DR
This study proposes an AI-enabled autonomous drone framework for infrastructure inspection that integrates intelligent flight planning, automated data collection, computer vision-based defect detection, and condition assessment that enhances inspection accuracy, operational safety, and scalability compared to traditional methods.
Abstract
Infrastructure assets such as bridges, roads, highways, tunnels, dams, power transmission lines, and high-rise buildings require regular inspection to ensure safety and reliability. Conventional visual inspection methods are time-consuming, expensive, and often expose inspectors to hazardous environments. Autonomous monitoring drones (UAVs) provide a faster, safer, and more cost-effective alternative by using advanced sensors, GPS, cameras, and AI-based technologies to collect and analyze structural data. This study proposes an AI-enabled autonomous drone framework for infrastructure inspection that integrates intelligent flight planning, automated data collection, computer vision-based defect detection, and condition assessment. The system accurately identifies cracks, corrosion, and other structural defects while optimizing flight paths for improved efficiency. The proposed framework enhances inspection accuracy, operational safety, and scalability compared to traditional methods, demonstrating significant potential for modern infrastructure management. Future developments may integrate swarm intelligence, edge computing, and digital twins to enable fully autonomous infrastructure monitoring and maintenance.
The increasing use of Unmanned Aerial Vehicles (UAVs) in energy-sector operations- such as pipeline inspection, infrastructure monitoring, and remote asset surveillance- has highlighted critical limitations in predominantly manual and semi-automated drone systems. While current UAV deployments offer improved safety and efficiency over traditional inspection methods, their dependence on continuous human control and stable communication links restricts scalability, resilience, and operational autonomy in complex or hazardous environments. This paper presents a conceptual framework for (state) adaptive autonomous UAV systems designed to address these limitations. The proposed approach emphasizes the integration of intelligent sensing, perception, decision-making, control, and communication as coordinated layers capable of adjusting to changing operational conditions. Rather than focusing on specific implementations, the framework outlines how autonomy-driven design principles can enhance UAV reliability, reduce human intervention, and improve operational continuity in energy-sector applications. By positioning autonomy as a critical enabler rather than an optional feature, this work aligns with ongoing digital transformation and energy transition efforts. The paper discusses potential application scenarios within oil and gas, power infrastructure, and renewable energy systems, and highlights key challenges related to regulation, system validation, and future deployment. The proposed framework provides a foundation for further research and development toward resilient, intelligent UAV operations in the evolving global energy landscape.
G. I. Akanbi, O. Kolade, S. Akande et al.· SPE Nigeria Annual Internati...· 0 citations
Rapid urbanization, industrialization, and aging infrastructure have increased the need for efficient monitoring systems. Traditional manual inspections of bridges, tunnels, pipelines, dams, railway tracks, and industrial facilities are costly, time-consuming, labor-intensive, and risky. Autonomous inspection robots offer an advanced solution for smart infrastructure monitoring and maintenance. This study reviews autonomous inspection robots developed before February 2019, focusing on their design, navigation, sensors, communication systems, and control methods. These robots use technologies such as LiDAR, ultrasonic sensors, infrared cameras, thermal imaging, GPS, and wireless communication for real-time monitoring, defect detection, and predictive maintenance. Machine learning and computer vision further improve inspection accuracy. Different robot types, including wheeled, tracked, aerial, climbing, underwater, and hybrid robots, are compared based on mobility, adaptability, energy efficiency, and inspection performance. The paper also proposes an autonomous wheeled inspection robot using sensor fusion and computer vision for obstacle avoidance, wireless communication, and autonomous navigation. Results show that autonomous inspection robots improve safety, fault detection, and inspection efficiency compared to manual methods. Challenges such as power consumption, communication delays, localization errors, and sensor calibration are discussed. Future developments involving AI, IoT, cloud robotics, edge computing, swarm robotics, and digital twins are expected to enhance intelligent infrastructure monitoring systems.
Pooja Agarwal, Rakesh Chandra· International Journal of Int...· 0 citations
Pavement condition assessment is essential for effective road network management, as paved roads deteriorate over time due to traffic loading and environmental effects. Traditional pavement surveys rely on in-situ measurements and visual inspections to identify surface distresses such as cracking, raveling, and weathering. Although widely used, these methods are often labour-intensive, time-consuming, costly, and may disrupt traffic while exposing inspectors to safety risks. Recent advances in unmanned aerial systems (UAS) provide a promising alternative for pavement condition assessment. UAV-based surveys enable rapid data collection over large areas using high-resolution imaging and sensor technologies, which can be integrated with artificial intelligence (AI) techniques for automated pavement distress detection and analysis. In Egypt, the rapid expansion of the road network and increasing maintenance demands highlight the need for an efficient, continuous, and reliable pavement monitoring system. This study presents an Egypt-focused framework that links UAV data acquisition, AI-based distress detection, and PCI-based decision-making to support the integration of UAV-based pavement inspection into existing road management practices. This study supports an Egypt-focused framework for integrating UAV-based pavement inspection into existing road management practices. The proposed framework outlines UAV data acquisition, AI-based distress detection, and pavement condition evaluation workflows, while considering local environmental, operational, and regulatory constraints. The framework is informed by successful international applications and is intended to enable safer, faster, and more cost-effective pavement assessment to support sustainable road network management in Egypt.
Abdel-Halem A. Abdel-hamed, Abdallah Samir Abdallah, Ibrahim Elnaml et al.· IOP Conference Series: Earth...· 0 citations
Effective inspection and maintenance of dams are essential for infrastructure longevity, water resource management, and public safety. Historically, dam maintenance relied heavily on visual inspections, which were limited in scope and accuracy, especially in detecting internal structural issues such as seepage and foundational degradation. This paper presents an industry-oriented evaluation of Unmanned Aerial Vehicles (UAVs) as a transformative tool in modern dam inspection and maintenance. The study explores UAVs' capacity to enhance efficiency, safety, and precision in identifying structural anomalies, erosion, and environmental degradation. Survey data collected from contractors in the Saudi water sector provides insight into current adoption levels, operational challenges, and perceived benefits. Return on investment (ROI) and Strength, weaknesses, opportunities, and threats (SWOT) analysis applied to evaluate and validate UAVs' potential to modernize dam maintenance practices, while highlighting technical, financial, and regulatory constraints. This research underscores UAVs' scalable utility and calls for further industry engagement to overcome adoption barriers and unlock their full potential in dam maintenance.
A. Alzahrani, Mohammed Sulaiman· University of Bisha Journal...· 0 citations
Pipeline infrastructure carries oil, gas, water, and industrial fluids across vast distances, and require careful maintenance. Visual inspections, scheduled digs, inline gauging tools, etc. have been industry standards for years, but struggle with expensive operations, scheduled downtime, and the inability to provide continuous monitoring. Autonomous robots have the potential to improve pipeline inspection workflows. Some robotic inspection platforms are equipped with advanced locomotion technologies like wheels, tracks, as well as embedded sensor payloads to detect corrosion, cracks, leakage, etc. Optical inspections can be augmented with ultrasonic testing, magnetic flux leakage, thermal imaging, acoustic sensors to provide comprehensive pipeline assessments. AI and machine learning allow for increased automation of anomaly detection and failure prediction. Beyond sensing, data storage and transfer allows for processed information to be used by operational teams and management. Edge computing allows for time-critical processes to be run on-board, while cloud computing allows for data storage and big-data analysis. SCADA integration can connect robotic inspections to enterprise-level risk analysis. Current limitations of pipeline inspection robots include limited energy storage, complex data analysis, deployment in difficult terrains/depths, and a lack of skilled pipeline operators. Some areas of development include energy harvesting robots, swarm robotics for distributed inspection, and multi-modal sensing/data fusion.
Wegner Chukwuemeka Dulo, Jolly-Adjarho Ogheneakpobor· E3S Web of Conferences· 0 citations
Vehicle–railway bridge collisions represent a persistent safety challenge that can compromise transportation infrastructure, interrupt railway operations, and generate substantial economic losses. Conventional bridge inspection and monitoring practices often rely on periodic inspections or isolated sensing mechanisms, limiting their ability to provide timely collision detection and predictive decision support. Recent developments in structural health monitoring, wireless sensing, intelligent video surveillance, and supervised machine learning have created opportunities for designing integrated monitoring systems capable of identifying collision events while simultaneously assessing infrastructure conditions and supporting proactive maintenance strategies. This paper proposes a Predictive Supervised Learning Architecture for Automated Vehicle–Railway Bridge Collision Detection, Monitoring, and Safety Optimization, which integrates heterogeneous sensing technologies, structural health monitoring, supervised classification algorithms, and predictive risk analysis into a unified decision-support framework. The proposed architecture combines visual monitoring, vibration sensing, synchronized wireless sensor networks, and intelligent data processing to distinguish collision events from normal operational conditions while estimating structural damage severity and recommending appropriate response actions. The framework further incorporates continuous learning mechanisms to improve prediction accuracy using historical infrastructure data and validated collision records. A comprehensive review of existing structural monitoring techniques demonstrates that although significant advances have been achieved in vibration-based damage detection, wireless monitoring, and bridge instrumentation, limited research has focused on integrating supervised learning with real-time railway bridge collision management.
Dário Miguel Gomes dos Santos· International Journal of Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
