Simulating travel paths of construction site workers via deep reinforcement learning considering their spatial cognition and wayfinding behavior

Kim, Minguk; Ham, Youngjib; Koo, Choongwan; Kim, Tae Wan

doi:10.1016/j.autcon.2022.104715

Cited by 8 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When capturing a 10 m/s athlete at a rate of 30 frames per second (fps) using a regular camera, we can obtain 300 frames, with a movement of approximately 33 cm per frame. But workers' average speed is 1.38 m/s [39], the movement of which is approximately 5 cm per frame. This 5~33 cm per frame magnitude is in alignment with the value for head size (Figure 4) multiplied by a proper ratio.…”

Section: The Size Of the Head And The Range Of Motionmentioning

confidence: 99%

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Liu,

Zhou,

Wang

et al. 2024

Buildings

View full text Add to dashboard Cite

Real-time detection of workers is crucial in construction safety management. Deep learning-based detecting methods are valuable, but always challenged by the possibility of target missing or identity errors under complex scenarios. To address these limitations, previous research depended on re-training for new models or datasets, which are prohibitively time-consuming and incur high computing demands. However, we demonstrate that the better detecting model might not rely on more re-training of weights; instead, a training-free model can achieve even better performance by integrating head information. In this paper, a new head-detecting branch (55 MB) is added to the Keypoint Region-based Convolutional Network (Keypoint R-CNN, 226 MB) without altering its original weights, allowing for a less occluded head to aid in body detection. We also deployed motion information and anthropometric data through a post-processing module to calculate movement relationships. This study achieved an identity F1-score (IDF1) of 97.609%, recall (Rcll) of 98.173%, precision (Prcn) of 97.052%, and accuracy of 95.329% as a state-of-the-art (SOTA) method for worker detection. This exploration breaks the inertial attitudes of re-training dependency and accelerates the application of universal models, in addition to reducing the computational difficulty for most construction sites, especially in scenarios with an insufficient graphics processing unit (GPU). More importantly, this study can address occlusion challenges effectively in the worker detection field, making it of practical significance.

show abstract

Section: The Size Of the Head And The Range Of Motionmentioning

confidence: 99%

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Liu,

Zhou,

Wang

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…Song et al used Revit 2020 to develop a crowd emergency evacuation path optimization model, which significantly improved the efficiency of evacuation optimization [39]. Minguk Kim et al used machine learning to simulate the pathfinding methods of real construction workers and eventually obtained the workers' path of travel [40]. The Autodesk Revit platform has developed Path of Travel, which can model the path of travel based on the Revit 2020 platform and can generate the shortest path trajectory and travel time for a pedestrian between two selected points.…”

Section: Relationship Between Type and Size Of Nursing Unit Layout An...mentioning

confidence: 99%

A Study on the Layout of Hospital Ward Buildings in Cold Regions of China Based on the Efficiency of Nurse Rounds

et al. 2023

View full text Add to dashboard Cite

As an important public facility, the number, area, and scale of hospital buildings are growing rapidly. The efficiency of nurses’ rounds to beds is an important indicator of the efficiency of nursing units in ward buildings. Ward buildings occupy a very important position in the overall energy consumption of hospital building complexes. The type and scale of nursing unit floorplans are some of the key factors affecting the energy consumption of ward buildings. In this paper, three typical floorplan layout types of hospital ward buildings in cold regions of China are selected. The relationships between rounding efficiency, building energy consumption, floorplan layout, and building size were quantified using Origin based on linear regression and non-linear regression. The study showed that at 60 beds, the efficiency of nurse rounds was 35.68% higher in the double-corridor layout compared to the single-corridor. At 44 beds, the difference in average bed energy consumption between the double-corridor type and the single-corridor type is the greatest, with a 9.02% saving in energy consumption. This result confirms that the layout and scale of the ward building has a significant impact on the efficiency of nursing unit rounds and building energy efficiency.

show abstract

BitHist: A Precision-Scalable Sparse-Awareness DNN Accelerator Based on Bit Slices Products Histogram

Meng,

Xiao,

Gao

et al. 2023

Euro-Par 2023: Parallel Processing

View full text Add to dashboard Cite

Simulating travel paths of construction site workers via deep reinforcement learning considering their spatial cognition and wayfinding behavior

Cited by 8 publications

References 48 publications

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

Head-Integrated Detecting Method for Workers under Complex Construction Scenarios

A Study on the Layout of Hospital Ward Buildings in Cold Regions of China Based on the Efficiency of Nurse Rounds

BitHist: A Precision-Scalable Sparse-Awareness DNN Accelerator Based on Bit Slices Products Histogram

Contact Info

Product

Resources

About