Hubo Cai

Uncertainty-aware visualization and proximity monitoring in urban excavation: a geospatial augmented reality approach

BackgroundThis research aims to improve the urban excavation safety by creating an uncertainty-aware, geospatial augmented reality (AR) to visualize and monitor the proximity between invisible utilities and digging implements. Excavation is the single largest cause of utility strikes. Utility strikes could be prevented if the excavator operator were able to “see” buried utilities and excavator movement, and judge the proximity between them in real time. Geospatial augmented reality (AR) is an enabling technology for such knowledge-based excavation. It synergizes the geospatial utility locations and the excavator movement into a real-time, three-dimensional (3D) spatial context accessible to excavator operators. The key to its success is the quality of the utility location data.MethodsThis paper describes a dynamic approach to incorporate positional uncertainties of buried utilities into an uncertainty-aware, geospatial-AR system for real time visualization and proximity analysis. Uncertainties are modeled as probability bands (e.g. spatial bands with certain probabilities of enclosing the “true” location of utilities). Positional uncertainties are derived in real time by referring to its determinant, data lineage, the genesis and processes used to collect and interpret data.ResultsA computational framework, and a generic data model and its XML-format implementation are developed and tested. A method is developed to analyze the proximity in the context of positional uncertainties of both the utilities and the excavator movement.ConclusionsThis newly created approach is expected to contribute to the safety in urban excavation via the integration of Geoinformatics and construction informatics into an uncertainty-aware, geospatial-AR, with real time visualization and analytical capabilities.

A Framework of RFID and GPS for Tracking Construction Site Dynamics

Construction site is rugged, dynamic, and complex, involving large number of resources that intensively interact with each other with varying site activities. Being able to precisely locate, and track the site dynamics is critical to project management. Studies have explored the potential of the Radio Frequency Identification (RFID) technology in estimating the two-dimensional (2D) and three-dimensional (3D) locations of construction site objects at discrete time points. Information systems based on the RFID technology have emerged to assist decision-making in construction project management tasks. However, for the purpose of tracking the construction site dynamics, both capabilities of estimating the 2D and 3D locations of site objects at discrete time points and tracking the real-time movement of site objects must be incorporated in the tracking system, leading to a four-dimensional (4D) system. This paper presents the framework of a 4D tracking system to continuously track the 4D status of construction site dynamics. The framework consists of RFID, global positioning system (GPS) wireless sensor network and geographical information system (GIS). A prototype system was implemented based on the 4D framework and tested in a field experiment to verify the system implementation.

Enhanced Boundary Condition–Based Approach for Construction Location Sensing Using RFID and RTK GPS

AbstractThe radio frequency identification (RFID) technology has proven its potential in locating and tracking construction resources, a critical task in construction project control. However, the main challenge is how to achieve desired levels of locating accuracy. This paper presents an enhanced boundary condition method that incorporates the tag-reader angle and the reader geometric configuration factors to control the accuracy of a locating system that integrates RFID and real time kinematic (RTK) global positioning system (GPS). Controlled laboratory experiments were conducted to assess their effects and create quality control filters. This study demonstrated the relationship between the detecting range and the tag-reader angle and used it to separate valid/invalid boundary points. Spatial dilution of precision (SDOP) was formulated to measure the geometric configuration of readers forming the boundary constraint. Correlating SDOP to the locating error through a polynomial regression model, a mechani...

Geometric modeling of geospatial data for visualization-assisted excavation

Underground utility lines being struck by mechanized excavators during construction or maintenance operations is a long standing problem. Besides the disruptions to public services, daily life, and commerce, utility strike accidents lead to injuries, fatalities, and property damages that cause significant financial loss. Utility strikes by excavation occur mainly because of the lack of an effective approach to synergize the geospatial utility locations and the movement of excavation equipment into a real-time, three-dimensional (3D) spatial context that is accessible to excavator operators. A critical aspect of enabling such a knowledge-based excavation approach is the geospatial utility data and its geometric modeling. Inaccurate and/or incomplete utility location information could lead to false instilled confidence and be counterproductive to the excavator operator. This paper addresses the computational details in geometric modeling of geospatial utility data for 3D visualization and proximity monitoring to support knowledge-based excavation. The details of the various stages in the life-cycle of underground utility geospatial data are described, and the inherent limitations that preclude the effective use of the data in downstream engineering applications such as excavation guidance are analyzed. Five key requirements - Interactivity, Information Richness, 3-Dimensionality, Accuracy Characterization, and Extensibility - are identified as necessary for the consumption of geospatial utility data in location-sensitive engineering applications. A visualization framework named IDEAL that meets the outlined requirements is developed and presented in this paper to geometrically represent buried utility geospatial data and the movement of excavation equipment in a 3D emulated environment in real-time.

Life Cycle Approach to Construction Workspace Modeling and Planning

AbstractWorkspace planning is critical for effective construction planning and control, and workspace modeling is an essential part of computer-aided workspace planning. The existing construction four-dimensional (4D) models, which have gained popularity in construction as an effective tool for planning, control, and communication, lack efficient means to capture the dynamic nature of workspaces to avoid potential workspace conflicts in future construction. This paper presents a life-cycle approach to workspace modeling and planning by first investigating the dynamic nature of the workspace requirements of construction activities and then introducing a conceptual framework to format space usages into life-cycle workspace evolution patterns. Specifically, an object-oriented data structure was designed and implemented to incorporate workspace representation into construction product models, and a workspace identification and adjustment method was created to facilitate the creation of construction workspaces...

Integrated Processing of Image and GPR Data for Automated Pothole Detection

AbstractA pothole is a severe pavement distress that can compromise pavement rideability and safety and can be the cause of expensive damage claims. The detection and evaluation of potholes are predominantly manual and time-consuming. Although sensing technologies such as global positioning systems (GPS), stereovision systems, and ground penetrating radar (GPR) now can be combined to collect pavement condition data for assessment, the raw data returned by these sensors are often processed individually and separately. This isolated approach to data processing hinders the potential efficiency and effectiveness of multisensor systems. This paper proposes a method to integrate the processing of two-dimensional images and GPR data to automate accurate and efficient pothole detection. First, the images and GPR scans are preprocessed to filter out noise and enhance the essential clues related to potholes. Second, a novel pothole detector was designed by investigating the patterns of GPR signals reflected by poth...

Agent-Based Simulation of Labour Emergency Evacuation in High-Rise Building Construction Sites

Construction sites are vulnerable to natural and manmade disasters that impose direct threat to contractor employers. High-rise building projects are more critical in such emergency situations because of the need to evacuate a large number of laborers who are working on the different floors of the building. Occupational safety regulations require general contractors to establish employee emergency action plans that specify emergency evacuation procedures and escape route assignments. These emergency plans are usually evaluated and practiced using real life drills, which face some critical challenges related to egress practicality and changing construction environment, especially in high-rise building construction sites. To overcome these challenges, this paper presents a conceptual agent-based simulation framework that would support general contractors in evaluating labour emergency evacuation plans in high-rise building construction projects. The framework is designed to facilitate: 1) modelling of construction activities workspaces that represent the number and locations of activities crews; 2) representing labour egress behaviour using software autonomous agents; 3) modelling of the physical space and evacuation routes of the building; and 4) evaluating the performance of emergency action plans. The proposed framework should prove useful to general contractors and public safety officials in effectively analyzing emergency action plans.

Integrating Natural Language Processing and Spatial Reasoning for Utility Compliance Checking

AbstractUnderground utility incidents, such as utility conflicts and utility strikes, result in time and cost overruns in construction projects, property damages, environmental pollution, personnel injuries, and fatalities. A main cause of recurrent utility incidents is the noncompliance with the spatial configurations between utilities and their surroundings. Utility specifications usually contain textual descriptions of the spatial configurations. However, detection of spatial defects, according to the textual descriptions, is difficult and time consuming. This deficiency is because of the lack of spatial cognition in many rule-checking systems to process massive amounts of data. This study aims to automate utility compliance checking by integrating natural language processing (NLP) and spatial reasoning. NLP algorithm translates the textual descriptions of spatial configurations into computer-processable spatial rules. Spatial reasoning executes the extracted spatial rules following a logical order in ...

Integrating GIS and Microscopic Traffic Simulation to Analyze Impacts of Transportation Infrastructure Construction

AbstractInfrastructure rehabilitation is critical to assuring the proper functioning of a nation’s transportation infrastructure. While the goal of rehabilitation is typically to restore or improve the performance of the transportation system, the construction activity itself disrupts traffic and worsens the already-congested transportation network with unsafe work zones. Traffic simulation models are becoming widely used in evaluating such disruption in a controlled environment without physical implementation. Though rapid increase in computer processing power has made microscopic simulation feasible, developing valid models is still a tedious and time-consuming task that is prone to errors. This paper presents a study to automate development of microscopic traffic simulation models in a large-scale network by integrating the geographic information system (GIS) and microscopic traffic simulation. This study adopted an integration approach and developed a framework to combine GIS macro- and microscopic mo...

Life-Cycle Approach to Collecting, Managing, and Sharing Transportation Infrastructure Asset Data

AbstractTransportation asset management (TAM) demands a data-driven decision-making process to proactively maintain, preserve, and extend the long-term service life of transportation assets. State ...