Simulating Crowd Evacuation

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.

Modified social force model considering emotional contagion for crowd evacuation simulation

The combination of multi-agent technology and reinforcement learning methods has been recognized as an effective way which is used in path planning-based crowd simulation. However, the existing solution is still not satisfactory due to the problem in the mutual influence of agents. Therefore, an improved multi-agent reinforcement learning method (IMARL algorithm) is introduced. In this method, the intersection of the pedestrian trajectory extracted from the real video is first used as the state space for reinforcement learning. The crowd is grouped and the leader is selected. A bulletin board is added to the reinforcement learning algorithm of multi-agent to store the empirical knowledge of the learning process, and the navigation agent passes information between the leader and the bulletin board. The original social force model was improved, and the cohesive force of visual factors was added to the force formula. The IMARL algorithm is combined with the improved social force model for crowd evacuation simulation. Using a two-layer control mechanism, the leader in the upper layer uses the decision process based on the IMARL algorithm to select the path, and the individuals in the bottom group use the improved social force model to evacuate. The method of this paper not only solves the dimensionality disaster problem of reinforcement learning but also improves the convergence speed. The evacuation efficiency is effectively improved in crowd evacuation simulation experiments. In addition, it can also provide specific guidance scheme for crowd evacuation improvement and assistant decision support for the prevention and management of large-scale group trampling incidents.

Crowd Evacuation Modeling and Simulation Using Care HPS

Existing crowd evacuation simulation methods commonly face challenges of low efficiency in path planning and insufficient realism in pedestrian movement during the evacuation process. In this study, we propose a novel crowd evacuation path planning approach based on the learning curve–deep deterministic policy gradient (LC‐DDPG) algorithm. The algorithm incorporates dynamic experience pool and a priority experience sampling strategy, enhancing convergence speed and achieving higher average rewards, thus efficiently enabling global path planning. Building upon this foundation, we introduce a double‐layer method for crowd evacuation using deep reinforcement learning. Specifically, within each group, individuals are categorized into leaders and followers. At the top layer, we employ the LC‐DDPG algorithm to perform global path planning for the leaders. Simultaneously, at the bottom layer, an enhanced social force model guides the followers to avoid obstacles and follow the leaders during evacuation. We implemented a crowd evacuation simulation platform. Experimental results show that our proposed method has high path planning efficiency and can generate more realistic pedestrian trajectories in different scenarios and crowd sizes.

The crowd evacuation simulation is essential to provide important results for occupants, especially in the large capacity building compared to the human fire drill exercise. The strategy of evacuation such as the use of obstacles may need to be adapted by many organizations as an aid to help in visualizing and estimating the evacuation time during an emergency. During certain crowd events, they may consider the various setting of the object to ensure smoothness and effective crowd evacuation flow. In this paper, it aims to provide the simulation with 100-1000 agents and testing with obstacle using Anylogic tool and analysis of evacuation time validated using SPSS. The results show that the placement of obstacles near the exit way indeed can reduce the evacuation time and complies with the anti-arching phenomenon during evacuation.

With the continuous expansion of the city scale and urbanization, urban road networks are becoming increasingly complex. Moreover, severe and extreme weather events, earthquakes, and other natural disasters occur frequently. Therefore, how to effectively and quickly evacuate urban crowd in dynamic environments is an urgent issue. To carry out the above objective, an unmanned system-guided crowd evacuation method is proposed in the current study. In the proposed method, the robot can perceive the environment in a timely and accurate manner to generate the evacuation map via advanced information technologies such as the Internet of Things or urban brain. Subsequently, an improved elliptic tangent graph approach based on global and local information (ETG-GLI) is utilized to plan a feasible and short evacuation path in large-scale scenarios. Finally, a novel crowd evacuation model based on the social force model is proposed to simulate the actual crowd evacuation process in complex and large-scale environments. To test the performance of the proposed path planning method, 25 different scenarios are proposed to simulate complex urban crowd evacuation environments. The experimental results show that the proposed algorithm outperforms other competitors in terms of path planning ability and computational time. Three actual evacuation cases with 324 pedestrians are modeled to further test the performance of the proposed algorithm. The simulation results demonstrate that the unmanned system-guided crowd evacuation method can find a shorter evacuation path for reducing the evacuation time in three complex and large-scale environments when compared with three other methods. Therefore, the proposed algorithm is a highly effective and promising approach to provide useful decision support and guidance for actual urban planning and urban emergence management. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In modern cities, the population density is high and the road network is complex. To evacuate the crowd in a timely and safe manner, planning feasible and short paths in large-scale and complex environments is a critical and challenging task. Therefore, the present study aims to provide a novel method to plan high-quality evacuation routes to guide the pedestrian flow. The performance of the proposed approach is validated in 25 test scenarios and 3 real-world instances. Experimental results demonstrate that the proposed algorithm performs well in terms of path length and computation time. Moreover, the proposed crowd evacuation model can simulate the actual process of crowd evacuation.

Pedestrian movement occurs in evolutionary patterns the effect of which is to facilitate the access of people into and out of living spaces (areas, volumes). In this paper, we rely on the philosophy of Constructal design as applied physics, in order to uncover two fundamental features of evolutionary design for pedestrian evacuation from rectangular areas (e.g., lecture halls with seated occupants). First, the paper shows analytically that the aspect ratio of the floor area can be selected such that the total evacuation time is minimal. Second, the shape of the floor area of each aisle can be tapered such that the total evacuation time is decreased further. These two architectural features are confirmed by means of extensive and systematic numerical simulations of pedestrian evacuation, by using two numerical packages (Simulex and FDS + Evac).

The emergency sign system provides evacuation information and route guidance for people and plays an important role in crowd evacuation in case of emergency. This paper investigates crowd dynamics with emergency signs and mainly focuses on the influence of signs on crowd evacuation dynamics under the visual field-limited environment. A modified social force model is proposed by taking into account the evacuation guidance of signs and interaction force between the pedestrians and signs. The effects of quantity and locations of emergency signs and self-organization behavior on evacuation efficiency are explored by simulations. According to the simulation results, the crowd evacuation with emergency signs shows an orderly evacuation process and the evacuation time is reduced significantly compared with that without signs in a smoke-filled room scenario. Moreover, emergency signs with appropriate locations and quantity are more conducive to crowd evacuation. Besides, the herding behavior can also improve the crowd evacuation efficiency.

The use of Crowd Simulation for re-enacting different real life scenarios has been studied in the literature. In this field of research, the interplay between ambient assisted living solutions and the behavior of pedestrians in large installations is highly relevant. However, when designing these simulations, the necessary simplifications may result in different ranges of accuracy. The more realistic the simulation task is, the more complex and computational expensive it becomes. We present an approach towards a reasonable trade-off: given a complex and computational expensive crowd simulation, how to produce fast crowd simulations whose results approximate the results of the detailed and more realistic model. These faster simulations can be used to forecast the outcome of several scenarios, enabling the use of simulations in decision-making methods. This work contributes with a simplified faster simulation model that uses a graph of queues for modeling an environment where a set of agents will navigate. This model is configured using Genetic Algorithms (GA) applied to data obtained from complex 3D crowd simulations. This is illustrated with a proof-of-concept scenario where a 3D simulation of one floor of a faculty building, with its corresponding students, is re-enacted in the network of queues version. The success criteria are achieving a similar total number of people in particular floor areas along the simulation in both the simplified simulation and the original one. The experiments confirm that this approach approximates the number of people in each area with a sufficient degree of fidelity with respect to the results that are obtained by a more complex 3D simulator.

An investigation of fire evacuation performance in irregular underground commercial building affected by multiple parameters

How to accurately simulate the real collective behavior of pedestrian evacuation remains an important issue in research of complex systems. The existing crowd simulation models in general assumed that pedestrians move directly towards the exit. In real life, however, there exist “cautious” pedestrians who fear trampling and crowding during evacuation, so we use an improved social force model to investigate how their presence influences evacuation dynamics. Simulation results reveal that the total evacuation time does not increase monotonically with the increment of the number of cautious pedestrians. Specifically, the presence of a moderate number of cautious pedestrians with rational psychological tolerance might substantially facilitate evacuation efficiency, compared with a conventional evacuation scenario. In addition, lower psychological tolerance promotes emergency evacuation, while increasing the tolerance threshold is conducive to slow evacuation. We hope that our research will provide some insights into the reasonable optimal strategies for emergency evacuation.

As safety sciences become more prominent, BIM-based simulations are attracting greater interest from various domains, from fire engineering to crowd management. The integration of BIM with advanced simulation tools and technologies has significantly advanced the field of hazard and crowd evacuation simulations. By providing detailed, dynamic, and interactive models, BIM enhances the accuracy and effectiveness of emergency planning and response strategies. This paper targets the development of a dynamic building model that can facilitate BIM-based fire protection and evacuation planning and training. In current practice, the building model is input to simulation tools as a static model. The latter provides comprehensive information about the building, but this information is static and represents the building in an idealized state where no changes are happening over time. We propose an ontological multi-model framework by extending the information container for linked document delivery (ICDD) implementation, ISO 21597, to a dynamic multi-model container aiming to explicitly allocate multiple dynamic values to elements in the building model. This enables consideration of changeable building spaces during the simulation runtime and hence real-time interoperability of the interlinked simulation components and modules.

CellEVAC: An adaptive guidance system for crowd evacuation through behavioral optimization

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.