AUGMENTED REALITY-BASED EVACUATION SIMULATION TO STUDY CROWD BEHAVIORS (original) (raw)
Related papers
A Review of Augmented Reality Applications for Building Evacuation
Evacuation is one of the main disaster management solutions to reduce the impact of man-made and natural threats on building occupants. To date, several modern technologies and gamification concepts, e.g. immersive virtual reality and serious games, have been used to enhance building evacuation preparedness and effectiveness. Those tools have been used both to investigate human behavior during building emergencies and to train building occupants on how to cope with building evacuations. Augmented Reality (AR) is novel technology that can enhance this process providing building occupants with virtual contents to improve their evacuation performance. This work aims at reviewing existing AR applications developed for building evacuation. This review identifies the disasters and types of building those tools have been applied for. Moreover, the application goals, hardware and evacuation stages affected by AR are also investigated in the review. Finally, this review aims at identifying the challenges to face for further development of AR evacuation tools.
COMPARISON OF CROWD SIMULATION FOR BUILDING EVACUATION AND AN ALTERNATIVE APPROACH
2007
This paper presents an overview of crowd simulation models, their limitations, and an alternative agentbased approch. First we introduce several methods and then we focus on two widely used and validated simulation tools that use grid-based models. We discus the artifacts that these models introduce regarding the way they treat the space and the implication that this has in the movement of the agents during the simulation. We also describe the limitations that current commercial software tools have in terms of simulating human psychology and physiology. The paper discusses an agent-based alternative approach developed to overcome these limitations. The model allows for the simulation of human movement that can provide results more closely describing behavior of real people during an emergency situation. Flow rates, densities and speeds emerge in our model from the physical interactions between people instead of being predefined.
OpenGL 3D crowd evacuation simulation at universiti tun hussein onn malaysia (UTHM) hostel
Indonesian Journal of Electrical Engineering and Computer Science, 2019
Crowd simulation is the process of simulating characterized agents or entities using computer application to analyse it in virtual scene or virtual environment. This paper investigates the best route path for agents to act in avoiding the fire hazards with different designated type of stairs in shop lots that were converted to hostel dormitory for students. 3D social force agent’s model and 3D fire hazards were designed in Microsoft Visual Studio C++ software and OpenGL library. A research was conducted using social force model behaviour and were taken by 10 and 15 agents to analyse the time taken to complete the evacuation process. The acceleration produced where it is related with route path taken by agents, interaction forces of agents and interaction forces of wall are the main research system to analyse agents’ behaviour during simulation. Different simulations have been used to determine the best and fastest route taken by agents. In summary, the lower the number of agents, th...
Safety Science, 2020
Evacuation models are key tools to assess the fire safety of complex buildings. Those tools and their results rely on the input values selected by users based on existing datasets and the way they are transformed into output. Several evacuation studies have been carried out to provide input values for evacuation models. However, those regarding healthcare facilities evacuation are still rare in the literature. In this paper, we present a new evacuation dataset for healthcare facility evacuation simulation. The data was collected from an outpatients' area of a public hospital in Auckland (New Zealand) during two unannounced fire drills. The video images were analysed to generate new evacuation model inputs for healthcare facility evacuation scenarios. The drills involved both staff and patients. Pre-evacuation times, evacuee horizontal travel speeds, exit selection and total evacuation times were collected and analysed. Moreover, we investigated evacuee reactions and actions to study staff and patients' interaction during the evacuation process. The results showed that pre-evacuation time of patients ranges from 8 to 63 s; while, pre-evacuation time of staff ranges from 8 to 141 s. In addition, during the movement phase, staff who were not assisting patients, and patients with no impairments, travelled at a similar average walking speed (i.e. 1.06 m/s for staff members and 0.93 m/s for patients with no impairments). Finally, the results indicated that the average travel speed of patients with walking impairments and staff assisting them was almost half of the travel speed of the first two groups (i.e. 0.52 m/s).
Pedestrian and Evacuation Dynamics 2012, 2013
A general challenge during a building emergency evacuation is guiding crowd to the best exits, given potential hazards and blockages due to high density use. Although computer simulation programs such as FDS+Evac allow researchers to evaluate various guidance policies under different circumstances, computational complexity limits their use during an actual emergency. A second limitation of such programs currently available is that they can only model certain psychological variables that affect evacuation. We suggest two innovations to address these difficulties. First, using macroscopic models, mathematical techniques can allow for rapid optimization of guidance that could eventually be used to provide real-time guidance during emergencies. Second, we conduct virtual reality experiments using human participants to provide confirmation of our models, and provide insights into how psychological factors not yet available in FDS+Evac will affect evacuation outcomes. Results of an initial VR experiment are presented.
Crowd Simulation Applied to Emergency and Evacuation Scenarios
Advances in Artificial Transportation Systems and Simulation, 2015
In recent years crowd modeling has become increasingly important both in the computer games industry and in emergency simulation. This paper discusses some aspects of what has been accomplished in this field, from social sciences to the computer implementation of modeling and simulation. Problem overview is described including some of the most common techniques used. Multi-Agent Systems is stated as the preferred approach for emergency evacuation simulations. A framework is proposed based on the work of Fangqin and Aizhu with extensions to include some BDI aspects. Future work includes expansion of the model's features and implementation of a prototype for validation of the propose methodology.
Simulation and Modelling the Human Crowd Evacuation
IOP Conference Series: Materials Science and Engineering
The operational research (OR) become one of emerging areas and significance and its relevance to be used in the simulation and modelling. To simulating and modelling the crowd evacuation, the most important elements to have in a realistic model is the appropriate simulation technique. To simulate the evacuee's movement in crowd is still in research and challenge because of the emergence and become a complex task and dangerous for the real and actual case. The computational simulation technique is required in order to model the crowd evacuation as one part of OR and become a solution to represent the fire crowd evacuation in the closed space e.g. Building relates to human movement and its states. The theories and concept of computational method allows for creating, analysing and experimentation. The techniques; Agent-Based Simulation (ABS), Social Force Model (SFM) and the hybrid SFM/ABS has been proposed for this research work. SFM is the well-known and popular technique for crowd evacuation while ABS is best-known, intelligent and appropriate to imitate the human movement. This paper provides a review of this research work from an OR perspective and the outcomes of a review of the computational simulation techniques literature are presented, using a proposed conceptual model will be valuable for future researchers, and modellers alike.
Modeling Crowd and Trained Leader Behavior during Building Evacuation
IEEE Computer Graphics and Applications, 2006
M any applications can benefit from animated virtual crowds. These applications include site planning, education, entertainment, training, and human factors analysis for building evacuation, or other scenarios where masses of people gather such as sporting events, transportation centers, and concerts.
Analyzing Large-Scale Crowd Simulations for Building Evacuation
Advances in Intelligent and Soft Computing, 2010
Animated virtual crowds have been used last years for analyzing human factors in scenarios where masses of people gather, such as sporting events, transportation centers, and concerts. A typical example is building evacuation in case of fire. Scalability still remains as an open issue for these multi-agent systems applications. In this paper, we use a scalable architecture to simulate a large-scale version of a virtual crowd in a building evacuation. From the social point of view, the results provided by the large-scale version of the crowd add new and crucial information about the agents behavior, emphasizing the need for a small amount of trained leaders in order to save lives. From the system point of view, the results show that the trend of avatars towards crowding in some areas highly increases the computation time for the agents hosted in some client computers. Therefore, this trend should be taken into account when designing large-scale evacuation simulations.
Evaluation of augmented reality technology for the design of an evacuation training game
Virtual Reality, 2019
Building evacuation training systems and training employees in an organization have a vital role in emergency cases in which people need to know what to do exactly. In every building, procedures, rules, and actions are attractively shown on the walls, but most of the people living in that building are not aware of these procedures and do not have any experience what to do in these dangerous situations. In order to be able to apply these procedures properly in an emergency situation, community members should be trained with the state-of-the-art equipment and technologies, but to do so, up-front investment and development of such a system are necessary. In this study, augmented reality (AR) technology was applied to realize a game-based evacuation training system that implements gamification practices. The architectural plans of a university were used to model the floors and the relevant environment. Employees are trained to learn how to reach the nearest exit location in the event of a fire or earthquake, and also, the system provides the shortest path for the evacuation. In addition to these features, our training game has educational animations about the fire, chemical attack, and earthquake events. A mobile application was implemented to train employees working in the building and inform them to know how to escape in an emergency situation. The technology acceptance model and the related questionnaire form were applied, and the response of 36 participants was analyzed. It was demonstrated that AR and relevant tools provide a flexible environment to develop evacuation systems in a university, our mobile application enabled participants to be trained in a realistic environment, and trainees were highly satisfied with the system. Educational animations were also another benefit for the trainees.