Search

This article explores the potential of the Unreal Engine as a tool for creating realistic 3D visualizations of large-scale areas (1000 km2 and more) using GIS datasets. Unlike small-scale visualizations, large-scale visualizations are rare and often not public, which presents significant problems since they present different challenges and require different approaches. This article presents several relevant scientific studies and projects that have successfully used game engines for similar purposes. This case study focuses on the computational techniques used in Unreal Engine for the 3D visualization of GIS data and the potential application of Unreal Engine in large-scale geo-visualizations. It explores the potential for using GIS data within a game engine, including plug-ins that provide additional functionality for working with GIS data, such as the Vitruvio plug-in to implement procedural modeling of buildings. The case study is applied to GIS datasets of the historical Vltava Valley covering an area of 1670 km2 to demonstrate the unique challenges of using Unreal Engine to create realistic visualizations of large-scale historical landscapes. The resulting visualizations are presented. The practical application of this research provides insights into the potential of the Unreal Engine as a tool for creating realistic 3D visualizations of large-scale historical areas.

The seismic response detection and operational safety assessment of high-speed railway (HSR) bridges play a crucial role in ensuring HSR systems’ operational safety and reliability. Smartphones have introduced intelligent inspection tools for structural health detection, becoming a new tool for intelligent structural inspection. Combining the public and smartphones is the key to public participation in structural health detection. This study utilizes smartphone-based structural seismic response inspection technology to investigate the framework of public participation in earthquake response inspection and assessment. This system comprises the Smart Bridge Brain (SBB), which integrates data from multiple sources and systems, an assigning mechanism for public participation inspection tasks, and smartphone-based HSR bridge structural seismic response inspection technology. At the same time, the Unreal Engine 5.0 software is used to create a mixed-reality virtual simulation experimental environment to validate the feasibility of this framework. The results indicate that the intelligent optimization of task allocation by the SBB successfully assigns detection tasks to each public participant. Public participants can promptly reach predefined damage structure detection targets and rapidly inspect bridge structural seismic response indicators using smartphones. In addition, this paper also conducts a comprehensive evaluation and analysis of the detection of the work efficiency index (WEI) within the system. Furthermore, optimization strategies for the efficient execution of detection tasks are proposed based on WEI variations influenced by different factors. The system framework is expected to enhance cluster-based HSR bridges’ intelligent disaster prevention and mitigation capabilities.

Although digital twins have been established in manufacturing for a long time, they are only more recently making their way into the urban environment and present a relatively new concept for the construction industry. The concept of a digital twin—a model of the physical environment that has a real-time two-way link between the physical and the digital, with the virtual model changing over time to reflect changes in the real world—lends itself well to the continually changing environment of a construction project. Predictive capabilities built into a twin also have great potential for construction planning—including in supply chain management and waste disposal as well as in the construction process itself. Underpinning this opportunity is location data, which model where something is happening and when and can be used to solve a wide range of problems. In particular, location (the power of where) can integrate diverse data sources and types into a single system, overcoming interoperability challenges that are known to be a barrier to twin implementation. This paper demonstrates the power of location-enabled digital twins in the context of a highway construction project, documenting and addressing data engineering tasks and functionality development to explore the potential of digital twins in the context of two case studies—health and safety and construction monitoring. We develop two demonstrators using data from an existing construction project (building on data and requirements from industry partner Skanska) to build twins that make use of the powers of 4D data presentation offered by the Unreal Gaming Engine and CesiumJS mapping, while software development expertise is sometimes available to construction firms, we specifically explore to what extent the no-code approach available within Unreal can be deployed in this context. Our findings provide evidence to construction companies as to the benefits of digital twins, as well as an understanding of the data engineering and technical skills required to achieve these benefits. The overall results demonstrate the potential for digital twins to unlock and democratise construction data, taking them beyond the niche use of experts and into the boardroom.

The problems of information isolation, inefficiency, and paper-based data archiving in traditional highway survey and design methods are investigated in this paper. A novel digital sandbox platform framework was developed to promote the efficiency of route design, model data integration, and information sharing. Under the presented framework, an integrated application method for both the Building Information Modeling (BIM) and Geographic Information System (GIS) technologies was designed by using Unreal Engine technology. Firstly, a digital base model was established by integrating multi-disciplinary BIM model data and GIS three-dimensional (3D) multi-scale scene model data. On this basis, using Unreal Engine technology for visualization development, a digital sandbox platform with the data visualization, traffic organization simulation analysis, 3D spatial analysis, component information query, and scene switching functions was developed, which satisfies the 3D visualization and digitalization needs in the current highway planning and design. Additionally, the Analytic Hierarchy Process (AHP) was employed to analyze the impact of digital base model on the development and application of platform modules, including five crucial factors: data accuracy, data representation, multi-source data fusion, data management capability, and scene semantic representation. Finally, the research results indicate that the proposed digital sandbox platform framework provides users with a platform for integrated data management, information sharing, and 3D data visualization, while reducing design time by 30%, total design cost by 12%, and land occupancy rate by 10%.

To improve the rapidity of path planning for drones in unknown environments, a new bio-inspired path planning method using E-DQN (event-based deep Q-network), referring to introducing event stream to reinforcement learning network, is proposed. Firstly, event data are collected through an airsim simulator for environmental perception, and an auto-encoder is presented to extract data features and generate event weights. Then, event weights are input into DQN (deep Q-network) to choose the action of the next step. Finally, simulation and verification experiments are conducted in a virtual obstacle environment built with an unreal engine and airsim. The experiment results show that the proposed algorithm is adaptable for drones to find the goal in unknown environments and can improve the rapidity of path planning compared with that of commonly used methods.

Unmanned aerial vehicles (UAVs) have emerged as a highly efficient means of monitoring landslide-prone regions, given the growing concern for urban safety and the increasing occurrence of landslides. Designing optimal UAV flight routes is crucial for effective landslide monitoring. However, in real-world scenarios, the testing and validating of flight path planning algorithms incur high cost and safety concerns, making overall flight operations challenging. Therefore, this paper proposes the use of the Unreal Engine simulation framework to design UAV flight path planning specifically for landslide monitoring. It aims to validate the authenticity of the simulated flight paths and the correctness of the algorithms. Under the proposed simulation framework, we then test a novel flight path planning algorithm. The simulation results demonstrate that the model reconstruction obtained using the novel flight path algorithm exhibits more detailed textures, with a 3D model simulation accuracy ranging from 10 to 14 cm. Among them, the RMSE value of the novel flight route algorithm falls within the range of 10 to 11 cm, exhibiting a 2 to 3 cm improvement in accuracy compared to the traditional flight path algorithm. Additionally, it effectively reduces the flight duration by 9.3% under the same flight path compared to conventional methods. The results confirm that the simulation framework developed in this paper meets the requirements for landslide damage monitoring and validates the feasibility and correctness of the UAV flight path planning algorithm.

A realistic and visible dynamic simulation platform can significantly facilitate research on underwater robots. This paper uses the Unreal Engine to generate a scene that resembles real ocean environments, before building a visual dynamic simulation platform in conjunction with the Air-Sim system. On this basis, the trajectory tracking of a biomimetic robotic fish is simulated and assessed. More specifically, we propose a particle swarm optimization algorithm-based control strategy to optimize the discrete linear quadratic regulator controller for the trajectory tracking problem, as well as tracking and controlling discrete trajectories with misaligned time series through introducing a dynamic time warping algorithm. Simulation analyses of the biomimetic robotic fish following a straight line, a circular curve without mutation, and a four-leaf clover curve with mutation are carried out. The obtained results verify the feasibility and effectiveness of the proposed control strategy.

Machine vision based on deep learning is gaining more and more applications in structural health monitoring (SHM) due to the rich information that can be achieved in the images. Bolts are widely used in the connection of steel structures, and their loosening can compromise the safety of steel structures and lead to serious accidents. Therefore, this paper proposes a method for the automatic detection of the bolt loosening angle based on the latest key point detection technology using machine vision and deep learning. First, we built a virtual laboratory in Unreal Engine5 that could automatically label and generate synthetic datasets, and the datasets with bolts were collected. Second, the datasets were trained using the YOLOv7-pose framework, and the resulting model was able to accurately detect key points of bolts in images obtained under different angles and lighting conditions. Third, a bolt loosening angle calculation method was proposed according to the detected key points and the position relationship between neighboring bolts. Our results demonstrate that the proposed method is effective at detecting the bolt loosening angle and that the use of synthetic datasets significantly improves the efficiency of datasets establishment while also improving the performance of model training.

Due to the complexity of wetland ecosystems, wetlands have a wide area of alternating land and water zones and complex vegetation composition, making it challenging to achieve dynamic displays of virtual wetland scenes using three-dimensional modeling. This study proposes a workflow of game engine-based virtual wetland scene construction for the rapid modeling of virtual wetland scenes. The virtual wetland scene construction work utilized Poyang Lake as the primary research area. It integrated unmanned aerial vehicle data collection technology and geographic information technology with 3D (three-dimensional) modeling of wetland elements and scene program modeling of the game engine to complete the construction and dynamic development of virtual wetland scenes. In addition, it used various virtual reality technologies to display the virtual wetland scene. The virtual scene of Poyang Lake combined with actual data was more realistic and had higher simulation. In reality, the digital wetland scene of Poyang Lake realizes multiple forms of virtual experience and provides users with a profoundly immersive virtual experience. This comprehensive virtual scene workflow in the study can serve as a technical resource for building 3D scenes. It can also provide a technical reference for the digital twin watershed project of Poyang Lake, which has practical application value.

Throughout history, tools for engineering in the building industry have evolved. Due to the arrival of Industry 4.0, Computer-Aided Design (CAD) and Building Information Modeling (BIM) software have replaced the usage of pens, pencils, and paper in the design process. This paper describes the work required to design a large-scale immersive visit of a district under construction in a suburban area of Greater Paris, France. As part of this real estate project, called LaVallée, we have access to its city information model: all the BIMs of the works to be carried out including roads, terrain, street furniture, fountains, and landscaping. This paper describes all the technical operations necessary for the design of an immersive 3D model with a high level of detail of the neighborhood with its surroundings. The objective of this technical report was to provide practitioners with feedback on such an achievement based on industrial-level data. The development of the city model begins with the registration of all the BIMs from different firms in a common Geographic Information System: this gives the opportunity to confront the operational requirement of a construction phase and the actual current practice of architecture firms. A first prototype was developed using the archviz tool TwinMotion. In order to increase the realism of the model, we describe the creation of a pipeline in Unreal Engine with the automated tasks of material and mesh replacement and the lighting and landscape configuration. The main contribution of this work is to give relevant experience on building such a large-scale model, with the Python script when possible, as well as the necessary manual steps. It is a valuable contribution to the making of large-scale immersive visits with a high level of detail and their requirements.

The Cyber-Physical and Intelligent Robotics Laboratory has been digitally recreated, and it includes all the key elements that allow 6-axis industrial robots to perform PTP, LIN, and CIRC motions. Furthermore, the user can create a program with these motion types. The human–machine interface is also integrated into our system. It can also assist SMEs in developing their in-house training. After all, training on an industrial robot unit does not entail installation costs within the facility. Nor are there any maintenance and servicing costs. Since the lab is digital, additional robot units can be added or removed. Thus, areas for training or production can be pre-configured within each facility. Because of the customizability and virtual education format, there is no room capacity problem, and trainees can participate in the exercises in parallel. Exercises were also conducted to evaluate the program’s impact on teaching, and the results showed that using machine units can improve teaching. Even today’s digital labs cannot physically convey the sense of space or the relative weights of different elements in virtual space. Even with these features, individuals can operate a machine more effectively than relying solely on traditional, non-interactive demonstration materials.

As a part of “The Vltava River” project, it was necessary to create a visualisation of the historic Vltava River valley before the construction of the so-called Vltava Cascade (nine dams built in the Vltava River basin between 1930 and 1992). Vectorisations of the Imperial Obligatory Imprints of the Stable Cadastre, and a terrain model created from contour lines from the State Map 1:5000-Derived (SMO-5), prepared in an earlier phase of the project, were used as a basis for this visualisation. Due to the extent of the modelled area, which is approximately 1670 km2, and the available underlying data realistically usable for the visualisation, mainly procedural modelling with the use of the CGA shape grammar was chosen for the creation of 3D objects. These procedurally created 3D models were completed with more detailed models of landmark buildings created in CAD. The outcomes were used to establish a virtual reality (VR) application in the Unreal Engine software. The results are a 3D scene created in a form corresponding approximately to the state of the Vltava River valley in the 19th century, which is available for viewing via a web application, and a VR scene used for demonstration at exhibitions.

More and more cities are evolving into smart cities, increasing their attractiveness, energy efficiency, and users’ satisfaction. Lighting systems play an important role in the evolution process, thanks to their ability to affect city life at night along with people’s mood and behaviour. In this scenario, advanced lighting design methods such as virtual reality (VR) became essential to assess lighting systems from different points of view, especially those linked with the city users’ expectations. Initially, the review highlights a list of objective and subjective parameters to be considered for the lighting design of three main city areas/applications: roads, green areas and buildings. Besides, the state-of-art in using VR for outdoor lighting design is established. Finally, the Unreal game engine is used to analyse the ability of VR to take into account the lighting parameters, not yet investigated in current literature and to highlight the VR potential for augmenting lighting design. The results confirm the benefit of using VR in lighting design, even if further investigations are needed to establish its reliability, especially from the photometrical point of view.