IEEE Transactions on Industrial Informatics, Год журнала: 2024, Номер 20(11), С. 12726 - 12735
Опубликована: Июль 17, 2024
Язык: Английский
Automation in Construction, Год журнала: 2024, Номер 161, С. 105346 - 105346
Опубликована: Фев. 28, 2024
Язык: Английский
Процитировано
11
Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown
Опубликована: Март 3, 2025
Abstract Pavement crack measurement (PCM) is essential for automated, precise road condition assessment. However, balancing speed and accuracy on edge artificial intelligence (AI) mobile devices remains challenging. This paper proposes a real‐time PCM framework deployment, incorporating lightweight distillation network surface feature algorithm. Specifically, the proposed instance‐aware hybrid module combines feature‐based relation‐based knowledge distillation, leveraging instance‐related information efficient transfer from teacher to student networks, which results in more accurate segmentation model. Additionally, algorithm, based distance mapping relationships coordinate extraction, addresses issues with branching loss, enhancing efficiency. Real‐time was performed actual roads utilizing robot equipped an computing unit. The precision reached 84.37%, frame per second of 77.72. Compared ground truth, relative error average width ranged 6.42% 40.65%, while length varied between 1.48% 3.76%. These findings highlight feasibility assessment save maintenance costs.
Язык: Английский
Процитировано
1
Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2024, Номер unknown
Опубликована: Окт. 9, 2024
Abstract Recent advancements in construction robotics have significantly transformed the industry by delivering safer and more efficient solutions for handling complex hazardous tasks. Despite these innovations, ensuring safe robotic navigation intricate indoor environments, such as attics, remains a significant challenge. This study introduces robust 3‐dimensional (3D) mapping method specifically tailored environments. Utilizing light detection ranging, simultaneous localization mapping, neural networks, this generates precise 3D maps. It also combines grid‐based pathfinding with deep reinforcement learning to enhance obstacle avoidance dynamic settings. An evaluation conducted simulated attic environment—characterized various truss structures continuously changing obstacles—affirms method's efficacy. Compared established benchmarks, not only achieves over 95% accuracy but improves 10% boosts both efficiency safety margins 30%.
Язык: Английский
Процитировано
5
Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown
Опубликована: Март 3, 2025
Abstract Visual inspection is crucial for the maintenance of built infrastructures, facilitating early detection and quantification damage. Traditional manual methods, however, often require inspectors to access dangerous or inaccessible areas, posing significant safety risks inefficiencies. In response these challenges, this paper introduces a portable visual device (VID) integrated with three laser distance meters high‐resolution camera. The VID enhances efficiency by incorporating methods that accurately estimate camera's pose relative target surface determine scale factor precise damage quantification. proposed were validated through experimental validations, demonstrating their precision effectiveness. lab‐scale validation, angle estimation showed accuracy less than 3 degrees error, method discrepancies 1 mm, even when observation exceeded 20 degrees. Subsequent field experiments confirmed VID's capability detect measure microcracks as narrow 0.1 mm. Furthermore, successfully quantified non‐crack an error margin 1.84%, at challenging angles exceeding 45
Язык: Английский
Процитировано
0
Integrated Computer-Aided Engineering, Год журнала: 2025, Номер unknown
Опубликована: Март 19, 2025
This paper presents novel Gait Decomposition (GD) and Parameter Gradient (GPG) methods for enhancing snake robot control optimization. Snake robots face challenges in parameter tuning due to their complex dynamics the need preserve gait characteristics during control. GD fine-tunes parameters while maintaining prevent unintended changes application of serpenoid curves, typical robots. A key feature is use a motion matrix represent joint movements, ensuring preservation characteristics. methodology classifies robot’s as matrix, aiding addressing common challenge real-world scenarios. Furthermore, we introduce GPG algorithm, designed efficiently optimize by adjusting both curve function matrix. Simulations validate effectiveness our methods, showing that decomposed closely retains original gait’s achieves stable optimization under various conditions. Together, offer significant improvements control, adaptability, practical deployment robots, potentially expanding applications across domains.
Язык: Английский
Процитировано
0
Automation in Construction, Год журнала: 2025, Номер 174, С. 106120 - 106120
Опубликована: Март 21, 2025
Язык: Английский
Процитировано
0
Signal Image and Video Processing, Год журнала: 2025, Номер 19(7)
Опубликована: Май 13, 2025
Язык: Английский
Процитировано
0
Automation in Construction, Год журнала: 2024, Номер 168, С. 105783 - 105783
Опубликована: Сен. 23, 2024
Язык: Английский
Процитировано
2
Measurement, Год журнала: 2024, Номер unknown, С. 116045 - 116045
Опубликована: Окт. 1, 2024
Язык: Английский
Процитировано
2
Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2024, Номер unknown
Опубликована: Дек. 13, 2024
Abstract Construction robots are challenging the paradigm of labor‐intensive construction tasks. Imitation learning (IL) offers a promising approach, enabling to mimic expert actions. However, obtaining high‐quality demonstrations is major bottleneck in this process as teleoperated robot motions may not align with optimal kinematic behavior. In paper, two innovations have been proposed. First, traditional control using controllers has replaced vision‐based hand gesture for intuitive demonstration collection. Second, novel method that integrates both and simple environmental rewards proposed strike balance between imitation exploration. To achieve goal, two‐step training first step, an collection platform virtual reality utilized. algorithm used train policy Experimental results demonstrate combining IL can significantly accelerate training, even limited data.
Язык: Английский
Процитировано
2