Robotics in construction: A critical review of the reinforcement learning and imitation learning paradigms

Delgado, Juan Manuel Dávila; Oyedele, Lukumon O.

doi:10.1016/j.aei.2022.101787

Cited by 21 publications

(8 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach involves reinforcement learning, where robots can learn through feedback, and imitation learning, which has significant implications for robotics. The intersection of robotics, reinforcement learning, and construction is explored in [16], providing a comprehensive review of research findings. Dataset preparation is pivotal in these endeavors, as seen in [17], where a combined dataset of collected and captured images was utilized.…”

Section: Related Workmentioning

confidence: 99%

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Azizi,

Koskinopoulou,

Petillot

2024

Robotics

View full text Add to dashboard Cite

Globally, workplace safety is a critical concern, and statistics highlight the widespread impact of occupational hazards. According to the International Labour Organization (ILO), an estimated 2.78 million work-related fatalities occur worldwide each year, with an additional 374 million non-fatal workplace injuries and illnesses. These incidents result in significant economic and social costs, emphasizing the urgent need for effective safety measures across industries. The construction sector in particular faces substantial challenges, contributing a notable share to these statistics due to the nature of its operations. As technology, including machine vision algorithms and robotics, continues to advance, there is a growing opportunity to enhance global workplace safety standards and mitigate the human toll of occupational hazards on a broader scale. This paper explores the development and evaluation of two distinct algorithms designed for the accurate detection of safety equipment on construction sites. The first algorithm leverages the Faster R-CNN architecture, employing ResNet-50 as its backbone for robust object detection. Subsequently, the results obtained from Faster R-CNN are compared with those of the second algorithm, Few-Shot Object Detection (FsDet). The selection of FsDet is motivated by its efficiency in addressing the time-intensive process of compiling datasets for network training in object recognition. The research methodology involves training and fine-tuning both algorithms to assess their performance in safety equipment detection. Comparative analysis aims to evaluate the effectiveness of novel training methods employed in the development of these machine vision algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Azizi,

Koskinopoulou,

Petillot

2024

Robotics

View full text Add to dashboard Cite

show abstract

“…There has been notable interest in applying ANN methods to construction manufacturing, but unfortunately, this work has been outside the realm of process control. Examples cover a diverse range of topics including component design (Navarro-Rubio et al, 2020), visual task identification (Rashid & Louis, 2020), component progress tracking (Martinez et al, 2010), and construction robotics coordination (Delgado & Oyedele, 2022).…”

Section: Past Work and Its Limitationsmentioning

confidence: 99%

Optimization and evaluation of a neural network based policy for real-time control of construction factory processes

Zhou,

Flood

2024

ITcon

View full text Add to dashboard Cite

This paper focuses on the development, optimization, and evaluation of an intelligent real-time control system for the fabrication of precast reinforced concrete components. The study addresses the unique challenges associated with real-time control in the construction manufacturing industry, including high customization, uncertain work demand, and limited stockpiling opportunities. A production system model is built based on a real construction manufacturing factory to simulate real-world precast reinforced concrete component fabrication, and acts as the basis for the development and validation of the control system. A review of alternative decision-making techniques is presented to identify the most suitable for the control of construction manufacturing factories. Ultimately, an artificial neural network approach trained using a reinforcement learning strategy is selected as a promising technique for effective real-time control. The controller is developed and validated, and its performance is optimized using sensitivity analysis, which takes into account both the structure of the artificial neural network and the parameters of the reinforcement learning algorithm. The ANN-based control policy is applied to the sequencing of precast reinforced concrete component production, while a rule-of-thumb policy is used as a benchmark for comparison. The study demonstrates that the optimized ANN-based control policy significantly outperforms the standard rule-of-thumb policy. The paper concludes by providing suggestions for further advancement of the ANN-based approach and potential avenues to increase the control policy's scope of application in construction manufacturing.

show abstract

“…Finally, we will finalize our state-of-the-art review by referencing research that used reinforcement learning approaches, mostly in combination with deep learning methods. RL research has been developed in several topics, including robotics [113][114][115], design automation [25], energy management strategies for hybrid vehicles [43], parameter estimation in the context of biological systems [44,116,117], in facial motion learning [48,50,118], and have also been successfully applied in closed-world environments, such as games [51,54,119,120]. In the topic of image processing, some pertinent studies were found, especially using DRL [31,47,57,121].…”

Section: Research Using Reinforcement Learningmentioning

confidence: 99%

Developments in Image Processing Using Deep Learning and Reinforcement Learning

Valente,

António,

Mora

et al. 2023

J. Imaging

View full text Add to dashboard Cite

The growth in the volume of data generated, consumed, and stored, which is estimated to exceed 180 zettabytes in 2025, represents a major challenge both for organizations and for society in general. In addition to being larger, datasets are increasingly complex, bringing new theoretical and computational challenges. Alongside this evolution, data science tools have exploded in popularity over the past two decades due to their myriad of applications when dealing with complex data, their high accuracy, flexible customization, and excellent adaptability. When it comes to images, data analysis presents additional challenges because as the quality of an image increases, which is desirable, so does the volume of data to be processed. Although classic machine learning (ML) techniques are still widely used in different research fields and industries, there has been great interest from the scientific community in the development of new artificial intelligence (AI) techniques. The resurgence of neural networks has boosted remarkable advances in areas such as the understanding and processing of images. In this study, we conducted a comprehensive survey regarding advances in AI design and the optimization solutions proposed to deal with image processing challenges. Despite the good results that have been achieved, there are still many challenges to face in this field of study. In this work, we discuss the main and more recent improvements, applications, and developments when targeting image processing applications, and we propose future research directions in this field of constant and fast evolution.

show abstract

Robotics in construction: A critical review of the reinforcement learning and imitation learning paradigms

Cited by 21 publications

References 67 publications

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Comparison of Machine Learning Approaches for Robust and Timely Detection of PPE in Construction Sites

Optimization and evaluation of a neural network based policy for real-time control of construction factory processes

Developments in Image Processing Using Deep Learning and Reinforcement Learning

Contact Info

Product

Resources

About