Development of a Rule-Based Monitoring System for Autonomous Heavy Equipment Safety

Authors

Amirpooya Shirazi, University of Nebraska-LincolnFollow

First Advisor

Kyungki Kim

Committee Members

Chun-Hsing (Jun) Ho, Pei-Chi Huang

Date of this Version

7-2024

Document Type

Thesis

Citation

A thesis presented to the faculty of the Graduate College at the University of Nebraska in partial fulfillment of requirements for the degree of Master of Science

Major: Construction Engineering and Management

Under the supervision of Professor Kyungki Kim

Lincoln, Nebraska, July 2024

Comments

Copyright 2024, Amirpooya Shirazi. Used by permission

Abstract

Roadway construction work zones are constantly exposed to interactions among construction equipment, workers, and vehicles. Furthermore, ensuring safety in these areas is considered a challenging task due to the complexity of the environment. As shown in the rising trend of fatal accidents in roadway work zones, current OSHA regulations in construction safety are insufficient in effectively detecting unsafe situations and mitigating the risks. Furthermore, best practices, such as internal traffic control planning (ITCP), exhibit critical limitations requiring continuous monitoring of active work zones as well as adjustments to the site coordination plans due to the dynamic nature of work zone environments. To overcome the stated challenges, this study proposes an innovative solution by integrating sensing and perception technologies of Autonomous Vehicles (AVs) to detect unsafe situations around heavy construction equipment by integrating vision-based sensors that can produce contextual information about the situation around the heavy equipment. To perceive such information, a Robotics Operating System (ROS) based algorithm has been developed, along with various PointCloud processing techniques aimed to identify and report the location of workers and other vehicles. Moreover, a simulation-based methodology was introduced aimed to devise an integrated sensor placement scheme, to facilitate a thorough sensor deployment strategy for monitoring unsafe zones using the designed ROS-based algorithms through an interconnected network of vision-based sensors. Furthermore, the designed sensor arrangement combined with the pipelines underwent three major experiments, illustrating the work zone within an isolated environment. Firstly, the experiments aimed to gauge the efficacy of both human and vehicle localization components by comparing reported locations with predetermined ground truths. Secondly, they involved delineating various human trajectory scenarios to analyze the tracking capabilities of the framework. Lastly, the experiments entailed simulating sequential entrances and exits into unsafe zones to assess the framework's sensitivity and accuracy in monitoring these designated zones. By providing the equipment with a precise understanding of its environment, the framework has proven its potential to enhance safety protocols and prevent unforeseen and hazardous situations. Additionally, this study represents a critical step toward the integration of autonomous rules and technologies into roadway construction work zones.

Advisor: Kyungki Kim