Crowd Evacuation Research Articles

Crowd Evacuation Guidance Based on Combined Action Reinforcement Learning

Existing crowd evacuation guidance systems require the manual design of models and input parameters, incurring a significant workload and a potential for errors. This paper proposed an end-to-end intelligent evacuation guidance method based on deep reinforcement learning, and designed an interactive simulation environment based on the social force model. The agent could automatically learn a scene model and path planning strategy with only scene images as input, and directly output dynamic signage information. Aiming to solve the “dimension disaster” phenomenon of the deep Q network (DQN) algorithm in crowd evacuation, this paper proposed a combined action-space DQN (CA-DQN) algorithm that grouped Q network output layer nodes according to action dimensions, which significantly reduced the network complexity and improved system practicality in complex scenes. In this paper, the evacuation guidance system is defined as a reinforcement learning agent and implemented by the CA-DQN method, which provides a novel approach for the evacuation guidance problem. The experiments demonstrate that the proposed method is superior to the static guidance method, and on par with the manually designed model method.

Swarm intelligence, social force and multi-agent modeling of heroic altruism behaviors under collective risks

Terrorists usually choose to attack soft targets, with low self-protection abilities and resistance strengths, such as schools, campus, public squares, railway stations, etc. Under great panic, civilians attacked tend to escape aimlessly and disorderly. Hence, colliding, pushing, and trampling will take place and lead to indirect deaths and injuries. If some heroes with the spirit of altruism, coming from civilians, stand up and fight terrorists bravely, the injuries and deaths will be greatly reduced. Agent-based modeling is built to explore the role of heroes during terrorist attacks. The particle system of three categories of agents, civilians, terrorists & heroes, is built to simulate the Peshawar School Case in 2014. Multiple action rules and mechanisms are introduced, such as swarm intelligence, information communication, self-organized behaviors, and heroic behaviors. We run each simulation repeatedly for 100 times to obtain averaged (robust) outcomes. The optimal combination of parameters, which best matches real outcomes, will be solved accordingly. It indicates that: (a) the self-organizing of crowd behaviors greatly improves the survival rate of civilians. Hence, well-planned trainings of counter-terrorists emergence responses can enhance capabilities of civilians; (b) people should learn from birds’ swarm behavior in crowd evacuations. As a swarm intelligence pathway, small groups and information sharing during crowd escape simulations can greatly improve survival rates; and (c) the society should encourage more people to be altruistic heroes who are acting prosocially. Besides, it suggests that more heroes bring safer overall outcomes for civilians and even for heroes themselves.

Assessment model for the Stability Situation of Crowd Evacuation based on Thermodynamic Map

To solve the shortcomings of the conventional assessment methods for crowd evacuation stability, such as over-reliance on the experience of the judges, obvious subjectivity and time-space limitations, this paper proposes an assessment model for judgment on the stability situation of crowd evacuation. Furthermore, the scenarios of large-scale crowd evacuation is diverse, and the compositions of crowd, the causes of crowd trampling are different. So it is particularly important to analyze specific problems for different scenarios. However, different data acquisition and poor real-time performance are main practical problems of judgment on the stability situation of large-scale crowd evacuation. With regard to shortcomings and problems above, the assessment model proposed in this paper uses big data technology to figure out a real-time crowd distribution thermodynamic map and obtain the crowd distribution density data. According to the criterion of crowd stability proposed by the Green Guide in Britain, the assessment model is further constructed to judge the stability situation of large-scale crowd evacuation in real-time.

Human Behavior During Emergency Evacuation: Cell Transmission Model

This paper presents an extended cell transmission model to simulate an emergency evacuation of crowd in a supermarket scenario. The supermarket scenario with a daily shopping, an emergency exit and multiple parallel shelves is discretized into a set of regular hexagonal cells. First, we verify the validity of the model by comparing the results of the model with actual data obtained from a reported pedestrian evacuation experiment. To improve the realism of the simulation, we then include three characteristics of human behavior, the unadventurous effect, inertial effect, and panic psychology, in the model as parameters and apply the extended model to the supermarket scenario. By analyzing the pedestrian density distribution, fundamental diagrams, route choice, and total evacuation time, we determine that the parameters have a significant influence on the evacuation process. By establishing a minimization model, we confirm that the total evacuation time is the least when the pedestrians’ familiarity with the emergency exit is close to the ratio of the width of the emergency exit to the total width of the two exits. Moreover, by comparing two different methods to choose exits, we can conclude that the approach, by which all pedestrians choose the closer exit, is not always the most efficient evacuation strategy. This study is conducive to devise evacuation plans and design exit layouts in facilities similar to supermarkets.

A smart dynamic crowd evacuation system for exhibition centers

Abstract In this paper, we consider the problem of finding the safest evacuation route in a multi-exit exhibition center while the fire hazard spreads. We first propose a system composed of sensor nodes to collect pertinent safety data. We present a real-time dynamic evacuation system that considers the changing conditions in the risks associated with each hallway segment in terms of walking distance, heat, two major asphyxiant fire gases and congestion. Our system activates smart panels placed at major junctions of the hallways to guide evacuees towards the appropriate exit by displaying the proper escape direction. This work can pave the way towards the development of next-generation smart exhibition centers, where crowd safety is among the top priorities.

Entropy-Based Crowd Evacuation Modeling With Seeking Behavior of Social Groups

Emergency crowd evacuation, especially in congested indoor scenes, is an important issue in public areas’ daily management. Computer simulation is a widely adopted technique to study crowd evacuations and help design reasonable emergence plans due to its flexibility, convenience, and cost-effectiveness. In this paper, we propose ECEM, a novel evacuation model based on agent simulation. In ECEM, we consider a special individual behavior in the evacuation, called seeking behavior, which happens when relatives or friends (i.e., social groups) are in the crowd, and the members within a group may tend to seek each other once separated instead of evacuating alone. Moreover, we incorporate the crowd chaos based on Boltzmann entropy (i.e., crowd entropy) into ECEM to measure the evacuating population’s disorder level and present an adaptive velocity smoothing method using crowd entropy for updating individual’s velocity. Extensive simulation results demonstrate the effectiveness of ECEM and provide several insights on designing the evacuation strategies.

A Virtual Reality Simulation Method for Crowd Evacuation in a Multiexit Indoor Fire Environment

Evacuation simulations in virtual indoor fire scenes hold great significance for public safety. However, existing evacuation simulation methods are inefficient and provide poor visualized when applied to virtual reality (VR) simulations. Additionally, the influences of the interaction of evacuation processes on the choice of multiple exits have not been fully considered. In the paper, we propose a VR simulation method for crowd evacuation in a multiexit indoor fire environment. An indoor 3D scene model and character model, for studying the environmental factors that affect the multiexit selection of personnel during the fire process, are combined with environmental factors to enhance the evacuation route planning algorithm to improve the efficiency of the VR simulation of evacuation in the scene. In addition, a prototype system that supports multiple experience modes is proposed, and case experiment analyses are performed. The results show that the method described in this paper can effectively support the real-time simulation of indoor fire evacuations in virtual scenes, providing both reliable simulation results and good visualization effects.

Disaster and Pandemic Management Using Machine Learning: A Survey.

This article provides a literature review of state-of-the-art machine learning (ML) algorithms for disaster and pandemic management. Most nations are concerned about disasters and pandemics, which, in general, are highly unlikely events. To date, various technologies, such as IoT, object sensing, UAV, 5G, and cellular networks, smartphone-based system, and satellite-based systems have been used for disaster and pandemic management. ML algorithms can handle multidimensional, large volumes of data that occur naturally in environments related to disaster and pandemic management and are particularly well suited for important related tasks, such as recognition and classification. ML algorithms are useful for predicting disasters and assisting in disaster management tasks, such as determining crowd evacuation routes, analyzing social media posts, and handling the post-disaster situation. ML algorithms also find great application in pandemic management scenarios, such as predicting pandemics, monitoring pandemic spread, disease diagnosis, etc. This article first presents a tutorial on ML algorithms. It then presents a detailed review of several ML algorithms and how we can combine these algorithms with other technologies to address disaster and pandemic management. It also discusses various challenges, open issues and, directions for future research.

Crowd evacuation simulation method combining the density field and social force model

Guiding crowd evacuation through changes in crowd density is one of the hot spots in crowd simulation research. Crowd evacuation methods can intuitively guide crowds to avoid high-density areas and improve evacuation efficiency. However, these methods are limited in accounting for the overall situation and lack realism. Therefore, this paper proposes a crowd evacuation method based on a density navigation algorithm. In the proposed method, a density navigation field model based on an equipotential field is first established. The model uses changes in the amount of charge to respond to changes in the density of the crowd, forming a density field. Second, this paper proposes a density navigation algorithm that guides the target selection in the process of crowd movement by calculating the density factor and distance factor. Finally, the density evacuation algorithm is combined with the social force model (SFM) to perform crowd evacuation simulation using a two-layer mechanism. The upper layer uses the density navigation algorithm for path planning, and the bottom layer uses the social force model to guide the evacuation. The experimental results show that the method effectively improves the crowd evacuation efficiency and can provide auxiliary decision support for large-scale group gathering events.

Emergency and disaster management-crowd evacuation research

This paper analyzes literatures on crowd evacuation based on data extracted from Web of Science by applying bibliometric approaches. In specific, reference co-citation analysis, author co-citation analysis, and keyword co-occurrence analysis are adopted to analyze the data with CiteSpace and VOSViewer. This paper makes the following contributions. First, reference co-citation analysis identifies five clusters in the studies on crowd evacuation. Second, author co-citation analysis identifies highly cited authors and categorizes them into three groups. Third, keyword co-occurrence analysis identifies the hotpots in the field of crowd evacuation and points out the directions for future studies.

An Improved Simulation Model for Pedestrian Crowd Evacuation

This paper works on one of the most recent pedestrian crowd evacuation models—i.e., “a simulation model for pedestrian crowd evacuation based on various AI techniques”—which was developed in late 2019. This study adds a new feature to the developed model by proposing a new method and integrating it into the model. This method enables the developed model to find a more appropriate evacuation area design regarding safety due to selecting the best exit door location among many suggested locations. This method is completely dependent on the selected model’s output—i.e., the evacuation time for each individual within the evacuation process. The new method finds an average of the evacuees’ evacuation times of each exit door location; then, based on the average evacuation time, it decides which exit door location would be the best exit door to be used for evacuation by the evacuees. To validate the method, various designs for the evacuation area with various written scenarios were used. The results showed that the model with this new method could predict a proper exit door location among many suggested locations. Lastly, from the results of this research using the integration of this newly proposed method, a new capability for the selected model in terms of safety allowed the right decision in selecting the finest design for the evacuation area among other designs.

Simulation Model of Crowd Evacuation Navigation in a Multi-Obstacle Environment

The simulation of a crowd evacuating public buildings can be an important reference in planning the layout of buildings and formulating evacuation strategies. This paper proposes an agent-based crowd model; a crowd evacuation navigation simulation model is proposed for the multi-obstacle environment. We introduce the concept of navigation factor to describe the proximity of the navigation point to the exit. An algorithm for creating navigation points in multi-obstacle environment is proposed along with the global navigation and local navigation control algorithms of the crowd. We construct a crowd evacuation simulation prototype system with different simulation scenes using the scene editor. We conduct the crowd evacuation simulation experiment in the multi-obstacle scene, recording and analyzing the relevant experimental data. The simulation prototype system can be used to derive the evacuation time of the crowd and analyze the evacuation behavior of the crowd. It is expected to provide a visual deduction method for crowd management in an evacuation emergency.

Intelligent robot-assisted evacuation: A review

Mass gathering in places such as shopping mall, concerts, sport events etc. is a necessity but may pose threat to the occupants during emergency. This paper presents a review of the different approaches of the crowd evacuation problems which can be classified into classical and modern methods. The classical methods have been widely used which basically depends on prior evacuation warnings or human in assisting an emergent evacuation scenario. Nonetheless, with the lack of important information such as the location of the safest exit, the consequence can be catastrophic. As a result, classical evacuation method becomes tough even though many people might able to assist the evacuees during such situation. Overcoming this, researchers have developed intelligent robots-assisted evacuation systems as a modern approach to manage crowds more systematically and simultaneously during emergency, which will be reviewed in this paper. Finally, this review paper aims to give a broad scope of the reliable evacuation system management to ensure the safety of the evacuees during emergency evacuation.

Influence of exits and evacuees on evacuation efficiency

In order to study the evacuation process of crowd in evacuation space containing four exits (two exits on one side), a simulation environment was built by using multi-agent simulation platform NetLogo, and the evacuation simulation model was constructed. The influence of exit location, exit width and evacuee number on the evacuation efficiency was studied, the results show that: with the exit moving to the middle, the evacuation time first decreases and then increases, and the decreasing rate of evacuation time decreases gradually and the increasing rate increases gradually; when the evacuee number is small, the evacuation time decreases with the increase of exit width, until the evacuation time remains unchanged when the exit width is large enough. However, when the evacuee number is large, the evacuation time in different positions decreases with the increase of exit width, and the overall decrease rate decreases; with the exit moving to the middle, the increasing rate of evacuation time with the increase of evacuee number at different exit widths decreases at first and then increases. The research results can provide some reference value for the evacuation exit design of building and emergency command of crowd evacuation.

EXPERIMENTAL STUDY TO COMPARE FACTORS INFLUENCING EXIT CHOICE BEHAVIOUR IN EMERGENCY EVACUATION SITUATIONS USING VIRTUAL REALITY TECHNIQUES

Abstract. Successful emergency evacuation of a large crowd depends on understanding human behaviour and its interaction with environmental stimuli in that situation. A careful study of human behaviour in these stressful and often time-bound situations can enable building designers to account for these effects to develop the most efficient evacuation strategies. One of the major roadblocks of the field has been the lack of reliable data collection techniques. Traditionally, most of the data analysed for these studies is either collected from historical events or through stated preference (SP) surveys given the challenges of conducting high-risk emergency evacuation experiments. The project is aimed at conducting emergency evacuation scenarios in a virtual reality (VR) environment. Eighty-four participants participated in multiple cases as a part of three VR scenarios to test various factors affecting their decision-making process. Participants were immersed in VR scenarios and subjected to a series of choices. Incorporation of VR technology enabled the experiment to record participants' stated preference with a much greater degree of certainty and realism as opposed to traditional pen and paper methods. The study devised a discrete choice model and calibrated it using the data obtained from the VR-based survey. When testing multiple competing factors in the VR scenarios and comparing the results with previous studies, in one VR scenario, the direction of exit signs was found more influential than crowding. In another scenario, familiarity with an exit appeared to be more influential than herding behaviour and exit distance. Overall, the VR technology is demonstrated to provide an advantage as a means to collect data and has come out as a promising tool to be incorporated in future emergency exit choice studies.

LED Wristbands for Cell-Based Crowd Evacuation: An Adaptive Exit-Choice Guidance System Architecture.

Cell-based crowd evacuation systems provide adaptive or static exit-choice indications that favor a coordinated group dynamic, improving evacuation time and safety. While a great effort has been made to modeling its control logic by assuming an ideal communication and positioning infrastructure, the architectural dimension and the influence of pedestrian positioning uncertainty have been largely overlooked. In our previous research, a cell-based crowd evacuation system (CellEVAC) was proposed that dynamically allocates exit gates to pedestrians in a cell-based pedestrian positioning infrastructure. This system provides optimal exit-choice indications through color-based indications and a control logic module built upon an optimized discrete-choice model. Here, we investigate how location-aware technologies and wearable devices can be used for a realistic deployment of CellEVAC. We consider a simulated real evacuation scenario (Madrid Arena) and propose a system architecture for CellEVAC that includes: a controller node, a radio-controlled light-emitting diode (LED) wristband subsystem, and a cell-node network equipped with active Radio Frequency Identification (RFID) devices. These subsystems coordinate to provide control, display, and positioning capabilities. We quantitatively study the sensitivity of evacuation time and safety to uncertainty in the positioning system. Results showed that CellEVAC was operational within a limited range of positioning uncertainty. Further analyses revealed that reprogramming the control logic module through a simulation optimization process, simulating the positioning system’s expected uncertainty level, improved the CellEVAC performance in scenarios with poor positioning systems.

Modeling and Simulation of Crowd Evacuation With Signs at Subway Platform: A Case Study of Beijing Subway Stations

Emergency signage systems provide effective route guidance and evacuation information for pedestrians in case of emergencies such as fire, blackout, and explosion. This paper proposes a modified social force (SF) model to investigate crowd evacuation dynamics taking into account the influence of emergency signs. The perceiving probability model is formulated for the quantitative description of the probability that pedestrians can successfully notice the sign and clearly perceive the guidance information. Simulation experiments and controlled experiments are designed to calibrate the parameters of the proposed model. The effectiveness of the modified SF model is preliminarily verified by comparing the simulation results with experimental data and/or empirical results such as fundamental diagrams and self-organization phenomena. A case study of crowd evacuation simulations at a typical Beijing subway station is conducted to evaluate evacuation performance of three signage distribution schemes, i.e., Maximal Covering (MaxCover), Uniform, and Random, which are proposed by the maximal covering location and empirical approaches, as well as contrasted scheme without emergency signs. The effects of the quantity and distribution of emergency signs on crowd evacuation efficiency are studied quantitatively by simulations. The results show that installing emergency signs can improve evacuation efficiency no matter what distribution scheme is adopted. By choosing an appropriate distribution scheme i.e., MaxCover, the evacuation performance can be further improved and the evacuation time can be significantly reduced.

Tangential Change Behavior and Pedestrian Simulation of Multichannel Evacuation Crowd

In evacuation, the velocity difference of adjacent pedestrians before and after often leads to tangential change of pedestrian location in channel. This tangential change behavior and its interaction disturb the stable state of crowd evacuation in multiple channels, which can affect the efficiency of crowd evacuation and even cause trampling accidents. This paper considers the dynamic comfort distance and the expected speed and analyzes the relative position changes after pedestrians change lanes. It investigates the conditions of tangential change behavior and defines the rules of tangential change behavior processing. Meanwhile, it investigates the crowd’s tangential change behavior and its interaction process, revealing the crowd evacuation mechanism of tangential change behavior conditions. Simulation results show that as the crowd density gradually increases, pedestrians exhibit the evolutionary characteristic of “no tangential change ⟶ occasional tangential change ⟶ frequent tangential change ⟶ closely following.” The evacuation speed is obviously influenced by pedestrian’s tangential change behavior and crowd density; when the pedestrian density ρ = 2.0 and ρ = 3.0 , the tangential change behavior not only makes the speed difference and fluctuation between different lanes great but also has the same effect on the average speed of pedestrians. The results of this study can provide theoretical insights into the organization of multichannel evacuation and expand the theoretical space of crowd dynamics in an evacuation.

A study of group effects in pedestrian crowd evacuation: Experiments, modelling and simulation

The presence of social groups in pedestrian crowds can have a substantial effect on the overall evacuation process. However, crowds are mostly simplified as a collection of individuals, and the influence of grouping has not been widely considered in pedestrian crowd simulations. In this study, a novel model that accounts for social groups was implemented based on a social force framework to investigate evacuation dynamics in pedestrian crowds. The associated model parameters were calibrated via two group experiments to provide more credible and realistic simulation results. The effects of certain variables (e.g., group size, desired speed, exit width) on the overall evacuation performance and local group behaviour were investigated. The simulation results indicate that group effects facilitated overall crowd evacuation, especially when the exit was wide. The total evacuation time of a pedestrian crowd was shorter when the groups within the crowd were larger. The time intervals for groups of various sizes did not show a significant difference. The group shape was approximated as a rectangle, and the group features were therefore quantified by shape-related parameters (e.g., aspect ratio and area). The rectangle was shown to orient itself along the moving direction. An elongated configuration of the group became increasingly notable when the leader–follower relationship intensified, resulting in a queue-like formation that facilitated the overall evacuation. A certain trend was found that showed an increase in the aspect ratio and a decrease in the normalised area over time. The larger-sized group often seemed to have a smaller aspect ratio but required more space per person during movement. This study deepens the understanding of crowd evacuation dynamics featuring social groups.

Strategies to Utilize the Positive Emotional Contagion Optimally in Crowd Evacuation

In a crisis situation, negative emotions often spread among the crowd, and they have adverse impacts on human decisions, resulting in stampedes and crushes. Safety officers are often dispatched to scenes of emergencies because their positive emotions can calm the crowd down and avoid serious accidents. However, how to utilize the positive emotional contagion to maximize the “calm-down” effect remains a challenging problem in crowd evacuation. In this paper, we present an approach for optimizing positive emotional contagion in crowd evacuation. First, a computational model of positive emotional contagion is proposed to describe how safety officers calm a crowd down. To capture important influential factors for positive emotional contagion, such as the trust relationships among the individuals involved in a crisis situation and the variations of emotional contagion speed, we construct a trust-based emotional contagion network (Trust-ECN) and a heterogeneous emotional contagion speed computation model (HECS-CM). Based on these models, the emotional contagion process can be analyzed in a parametric way, and the infection probability for each individual in a given time window can be computed analytically with a continuous-time Markov chain (CTMC). Second, a maximization problem of emotional contagion is formulated. Since this optimization problem is NP-hard, an artificial bee colony optimized emotional contagion (ABCEC) algorithm is used to solve for the optimal positions of safety officers. We demonstrate the effectiveness of our method on both synthetic and real-world data at different scales. Finally, we implement a crowd simulation system to visualize the results of our theoretical analysis in a graphical manner. The proposed method can provide guidance for emergency response management.