UV Disinfection Robots: A Review

Robotics and Autonomous Systems, Год журнала: 2022, Номер 161, С. 104332 - 104332

Опубликована: Дек. 9, 2022

Язык: Английский

---

The use of unmanned ground vehicles (mobile robots) and unmanned aerial vehicles (drones) in the civil infrastructure asset management sector: Applications, robotic platforms, sensors, and algorithms

Expert Systems with Applications, Год журнала: 2023, Номер 232, С. 120897 - 120897

Опубликована: Июнь 24, 2023

Язык: Английский

---

Iterative application of generative adversarial networks for improved buried pipe detection from images obtained by ground‐penetrating radar

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2023, Номер 38(17), С. 2472 - 2490

Опубликована: Июль 13, 2023

Abstract Ground‐penetrating radar (GPR) is widely used to determine the location of buried pipes without excavation, and machine learning has been researched automatically identify from reflected wave images obtained by GPR. In object detection using learning, accuracy affected quantity quality training data, so it important expand data improve accuracy. This especially true in case that are located underground whose existence cannot be easily confirmed. Therefore, this study developed a method for increasing you only look once v5 (YOLOv5) StyleGAN2‐ADA automate annotation process. Of particular importance developing framework generating generative adversarial networks with an emphasis on challenging detect YOLOv5 add them dataset repeat recursively, which greatly improved Specifically, F ‐values 0.915, 0.916, 0.924 were achieved step 500, 1000, 2000 images, respectively. These values exceed ‐value 0.900, manually annotating 15,000 much larger number. addition, we applied road Shizuoka Prefecture, Japan, confirmed can high real road. contribute labor‐saving expansion, time‐consuming costly practice, as result, contributes improving

Язык: Английский

---

A human-simulated fuzzy membrane approach for the joint controller of walking biped robots

Integrated Computer-Aided Engineering, Год журнала: 2023, Номер 30(2), С. 105 - 120

Опубликована: Фев. 7, 2023

To guarantee their locomotion, biped robots need to walk stably. The latter is achieved by a high performance in joint control. This article addresses this issue proposing novel human-simulated fuzzy (HF) membrane control system of the angles. proposed system, controller (HFMC), contains several key elements. first an HF algorithm based on intelligent (HSIC). incorporates elements both multi-mode proportional-derivative (PD) and control, aiming at solving chattering problem switching while improving accuracy. second architecture that makes use natural parallelisation potential computing improve real-time controller. HFMC utilised as for robot. Numerical tests simulation are carried out with planar slope walking five-link robot, effectiveness verified comparing evaluating results designed HFMC, HSIC PD. Experimental demonstrate not only retains advantages traditional PD but also improves accuracy, stability.

Язык: Английский

---

Object detection in hospital facilities: A comprehensive dataset and performance evaluation

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 123, С. 106223 - 106223

Опубликована: Апрель 11, 2023

Язык: Английский

---

Entropy-Weighted Numerical Gradient Optimization Spiking Neural System for Biped Robot Control

International Journal of Neural Systems, Год журнала: 2024, Номер 34(06)

Опубликована: Март 15, 2024

The optimization of robot controller parameters is a crucial task for enhancing performance, yet it often presents challenges due to the complexity multi-objective, multi-dimensional multi-parameter optimization. This paper introduces novel approach aimed at efficiently optimizing enhance its motion performance. While spiking neural P systems have shown great potential in addressing problems, there has been limited research and validation concerning their application continuous numerical, contexts. To address this gap, our proposes Entropy-Weighted Numerical Gradient Optimization Spiking Neural System, which combines strengths entropy weighting systems. First, introduction eliminates subjectivity weight selection, objectivity reproducibility process. Second, employs parallel gradient descent achieve efficient searches. In conclusion, results on biped simulation model show that method markedly enhances walking performance compared traditional approaches other algorithms. We achieved velocity mean absolute error least 35% lower than methods, with displacement two orders magnitude smaller. provides an effective new avenue field robotics.

Язык: Английский

---

Automating Building Damage Reconnaissance to Optimize Drone Mission Planning for Disaster Response

Journal of Computing in Civil Engineering, Год журнала: 2023, Номер 37(3)

Опубликована: Фев. 1, 2023

Rapid reconnaissance of building damage is critical for disaster response and recovery. Drones have been utilized to collect aerial images affected areas in order assess damage. However, there are two challenges. First, processing many detect classify based on a consistent standard remains laborious complex, necessitating new automated solution achieve accurate detection classification. Second, drone operations during rely primarily human operators' experience seldom use the obtained information optimize mission planning. Therefore, this study proposes method, which automates with planning operations. Specifically, deep learning method developed damages using newly labeled dataset consisting 24,496 distinct instances This validated, achieving 71.9% mean average precision. In addition, modeled integrated into planning, drones' task assignments route calculations. A tornado Tennessee used as case quantitatively evaluate methodology. The present concludes that optimal can be augmented acquired from methods.

Язык: Английский

---

Cross‐entropy‐based adaptive fuzzy control for visual tracking of road cracks with unmanned mobile robot

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2023, Номер 39(6), С. 891 - 910

Опубликована: Окт. 11, 2023

Abstract Visual tracking of road cracks in unstructured environment was, is, and remains a crucial challenging task, which plays vital role accurate crack sealing for automated repair. However, many problems have not been well solved existing repair, such as the low automation due to partial dependence on manual interrupted traffic flow caused by heavy equipment used. In this article, cross‐entropy‐based adaptive fuzzy control (CEAFC) method is proposed, reaches visual with unmanned mobile robot (VT‐UMbot) cracks. Specifically, CEAFC uses cross‐entropy optimization iteration tune parameters controller, logic constructed explore robustness improvement. Moreover, framework VT‐UMbot based four‐wheel independent differential drive established, servo are integrated into system. Our experiment shows that proposed extensively evaluated three scenarios achieves state‐of‐the‐art performance high efficiency.

Язык: Английский

---

Intention‐aware robot motion planning for safe worker–robot collaboration

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2023, Номер 39(15), С. 2242 - 2269

Опубликована: Дек. 5, 2023

Abstract Recent advances in robotics have enabled robots to collaborate with workers shared, fenceless workplaces construction and civil engineering, which can improve productivity address labor shortages. However, this collaboration may lead collisions between robots. Targeting safe collaboration, study proposes an intention‐aware motion planning method for avoid collisions. This involves two novel deep networks that allow anticipate the motions of based on inferences about workers' intentions. Then, a probabilistic collision‐checking mechanism is developed enables estimate collision probability generate collision‐free adjustments. The results verify predict intended 1 s advance adjustments less than 5.0% during collaborative masonry tasks. facilitates implementation engineering.

Язык: Английский

---

Automated detection of vehicles with anomalous trajectories in traffic surveillance videos

Integrated Computer-Aided Engineering, Год журнала: 2023, Номер 30(3), С. 293 - 309

Опубликована: Март 21, 2023

Video feeds from traffic cameras can be useful for many purposes, the most critical of which are related to monitoring road safety. Vehicle trajectory is a key element in dangerous behavior and accidents. In this respect, it crucial detect those anomalous vehicle trajectories, that is, trajectories depart usual paths. work, model proposed automatically address by using video sequences cameras. The proposal detects vehicles frame frame, tracks their across frames, estimates velocity vectors, compares them vectors other spatially adjacent trajectories. From comparison very different (anomalous) neighboring detected. practical terms, strategy wrong-way Some components off-the-shelf, such as detection provided recent deep learning approaches; however, several options considered analyzed tracking. performance system has been tested with wide range real synthetic videos.

Язык: Английский

---