Integrating AI in an Audio-Based Digital Twin for Autonomous Management of Roadway Construction

Document Type

Conference Proceeding

Publication Date

1-1-2022

Abstract

Construction of transportation infrastructure projects such as roadways generally involves a wide range of processes, participants, and machinery to successfully achieve the goal of a project. A systematic way of obtaining real-time data for effective and efficient management and communication is critically required for optimally managing logistics including ongoing construction activities and required resources. Recently, several studies have explored the concept of digital twin (DT) integrated with artificial intelligence (AI) technologies for real-time project organization and predictive analyses. This study proposes a new framework that integrates deep reinforcement learning (DRL) into an audio-based DT system for autonomous monitoring and management of paving activities in a roadway construction site. The objective of this study is to develop a framework that autonomously optimizes work cycles and resource allocation according to real-time site activities and data collected from diverse sensors. The framework obtained real-time data from the construction site through sensors and processed it on a cloud-based platform using DRL to autonomously optimize the work cycle and manage the resources involved in paving activity. This system is expected to be highly beneficial for reducing manual labor, idle time, human error, and wastage of resources in monitoring a gigantic-sized transportation construction site and managing complicated logistics.

Publication Source (Journal or Book title)

Construction Research Congress 2022: Computer Applications, Automation, and Data Analytics - Selected Papers from Construction Research Congress 2022

First Page

530

Last Page

540

This document is currently not available here.

Share

COinS