Multi-agent Evacuation Research Articles

Planning for service space of medium- and long-term shelters based on multi-agent evacuation simulation

Planning for service space of medium- and long-term shelters based on multi-agent evacuation simulation

Construction of the Simulation Algorithm for Evacuation of Commercial Complexes under the Panic Factor

In order to study the behavior and characteristics of crowd evacuation in buildings, and then organize crowd evacuation reasonably and efficiently in emergency, a simulation model of crowd evacuation in buildings is proposed, which not only accords with reality, but also comprehensively considers many factors. Aiming at the shortcomings of the crowd evacuation simulation model in the existing building emergency evacuation, this model provides a multi-agent evacuation simulation method and system based on panic emotion, which aims to more truly simulate the crowd evacuation process in emergency, and has important practical significance for the crowd evacuation plan in emergency and how to effectively organize crowd evacuation and reduce casualties in emergencies. In order to achieve the above goal, a multi-agent evacuation simulation method based on leaders and panic emotions is proposed. The method includes the following three stages: perception stage, decision-making stage and action stage, and each stage is explained step by step.

Multiagent evacuation framework for a virtual fire emergency scenario based on generative adversarial imitation learning

AbstractOne of the most common solutions for the prevention of fire accidents is to conduct extensive fire evacuation drills in crowded places. However, there are multiple salient advantages to using virtual reality technology to simulate emergency solutions, for instance, saving costs and greatly decreasing uncertain risks or accidents. Therefore, in this article, a multiagent evacuation framework for complex virtual fire scenarios is proposed and effectively used to simulate a multiagent evacuation procedure to approximate the goal of fire drills in a less costly manner. Specifically, the concept of a multihierarchy agent group model is proposed; that is, the evacuation of multiple agents is separated into leader‐follower and freedom modes. Additionally, several complex actions of individual humans in actual fire drills are fully considered, and a multiaction agent schema is presented to characterize the associated real effects. In addition, generative adversarial imitation learning is adopted to obtain the evacuation path of the leader‐agent by training numerous learning epochs. Finally, extensive experiments are conducted to validate the feasibility of our proposed method. The results show that the proposed method is superior to other methods and that it realistically and reasonably shows the procedure of multiagent evacuation in complex fire emergency scenarios.

Impact of evacuation design parameter on users' evacuation time using a multi-agent simulation

• Evacuation from indoor environment with multi-structure was studied by both experimental and modeling methods. • An evacuation model predicting disturbance in evacuation flow is tested. • User capacity and path selection affect the time taken to evacuate users. Emergency management is a fundamental issue in building management. Therefore, this study was established to simulate the required times and movement conditions for user evacuation from Campus Infrastructure Building in a 3D environment. Eight simulations are carried out by a multi-agent evacuation simulator, Pathfinder, considering 100% and 70% users capacity with a combination of random, divide, zone 1 and zone 2 access selection. The users evacuated were handled by the A* algorithm in the steering mode of 3D evacuation simulation. The evacuation flow was investigated with the user density heat map and Fruin’s Level of Service (LOS). This study found the best path planning obtained from the divide access factor and the impact of the user's capacity is relying on total evacuation time. The critical space is caused by the access width fewer than 1.5 m for every floor, and by widening some spaces helped to improve the evacuation flow.

Influence of Evacuation Walkway Design Parameters on Passenger Evacuation Time along Elevated Rail Transit Lines Using a Multi-Agent Simulation

Passenger evacuation on elevated railway lines has always been an important issue for elevated rail transit safety management, because it is challenging to evacuate passengers efficiently in the event of man-made calamities and natural disasters. Therefore, an evacuation walkway has been designed as a primary solution to assist passenger evacuation during an emergency on elevated rail transit lines. However, investigations on how evacuation walkway designs influence passenger evacuation time are still limited. This study established two evacuation scenarios of interval evacuation on elevated rail transit lines and put forward a new evacuation time measurement method, based on the concept of ‘evacuation time for passengers leaving the evacuation walkway risk zone’. Then, the evacuation time for 90 combinations of entrance widths and walkway widths was simulated by a multi-agent evacuation simulator, Pathfinder, considering 1032 passengers being evacuated both unidirectionally and bidirectionally. The results show that the entrance width and walkway width have a combined effect on passenger evacuation time. An increase in the walkway width from 0.7 m to 1.5 m may potentially reduce the evacuation time by 54.5% in unidirectional evacuation, and 35.2% in bidirectional evacuation. An increase in the entrance width results in a noticeable evacuation time fluctuation when the walkway width is 0.7 and 0.8 m for both evacuation scenarios, while in a bidirectional evacuation, a noticeable fluctuation also can be observed when the walkway width is within the range of 1.4–1.5 m. According to the study, a potentially good design parameter combination for a newly built evacuation walkway is 1.3 m and 1.4 m for the walkway width and entrance width, respectively. The findings from this study may provide a useful reference in the optimization of the design of evacuation facilities and improvement of passenger evacuation safety in rail transit systems.

Integrating multi-agent evacuation simulation and multi-criteria evaluation for spatial allocation of urban emergency shelters

ABSTRACTThe timely and secure evacuation of residents to nearby urban emergency shelters is of great importance during unexpected disaster events. However, evacuation and allocation of shelters are seldom examined as a whole, even though they are usually closely related tasks in disaster management. To conduct better spatial allocation of emergency shelters in cities, this study proposes a new method which integrates techniques of multi-agent system and multi-criteria evaluation for spatial allocation of urban emergency shelters. Compared with the traditional emergency shelter allocation methods, the proposed method highlights the importance of dynamic emergency evacuation simulations for spatial allocation suitability analysis. Three kinds of agents involved in evacuation and sheltering procedures are designed: government agents, shelter agents, and resident agents. Emergency evacuations are simulated based on the interactions of these agents to find potential problems, for example, time-consuming evacuation processes and road congestion. A case study in Jing’an District, Shanghai, China was conducted to demonstrate the feasibility of the proposed method. After three rounds of simulation and optimization, new shelters were spatially allocated and a detailed recommended plan of shelters and related facilities was generated. The optimized spatial allocation of shelters may help local residents to be evacuated more quickly and securely.

Information Exchange on MANET for Efficient Evacuation

In disaster situations, people need to evacuate from dangerous areas to safe ones. In particular, they must formulate an evacuation plan for themselves when they cannot obtain support. Communicating with other evacuees to obtain information is useful in formulating an evacuation plan, and some studies have used a mobile ad hoc network (MANET) for this purpose, because such a network can be constructed using only wireless devices even when a fatal situation arises. However, we cannot treat a MANET in the same manner as other networks (such as a carrier network or Wi-Fi), and MANETs have several shortcomings in regard to information exchange. It is necessary to investigate the effects of these limitations on creating evacuation support systems on a MANET. We evaluated whether the limited information exchange available using a MANET is sufficient to create evacuation support systems through the use of a multi-agent evacuation simulator. As a result, our simulator showed that limited communication in which people communicate only with neighbors provides substantial efficiency for evacuation. People can continue to evacuate effectively even if they cannot obtain all of the desired information owing to MANET limitations.

スタジアム・劇場等における避難性状のマルチエージェントシミュレーションによる予測

Evacuation flow on the spectator stands of stadia and theaters which consist of complicated evacuation route, such as gangways and gate etc. are examined with the multi-agent evacuation simulator SimTread (MA model). Through those examinations, characteristics of evacuation flow are obtained which should be carefully considered when we make evacuation safety planning. Major results are as follows; 1) Evacuees tend to remain backward of the radial gangways. 2) Merging rate at the radial gangways, lateral gangways, and exit gates change according to the merging condition and with time. 3) The cause of characteristic observed in 1) is analyzed in mathematically. This characteristic is well approximated by multiplier effect of merging rate and adjusted calculation method is proposed. 4) Theatres of cinema complex which have pitched spectator's seats and have exits only lower area are needed careful consideration for the tendency that evacuees remain high place from the viewpoint of smoke exposure.

Multi-agent based modeling and simulating for evacuation process in stadium

A multi-agent evacuation model is proposed in this paper to simulate the pedestrian evacuation process in stadium with or without obstacles. The authors give a multi-agent individual decision-making framework, in which the action direction of each pedestrian (called agent) is affected by the distance of the agent to the exits and the occupant number and density within the view field of the agent. Different from the existing results, the authors divide all the pedestrians in the stadium into four classes: Young male, young female, old male, and old female. In evacuation process, the weighting that affects individual decision-making between each class of agents is different. In the simulation, the authors present the effects of obstacles, crowd distribution and the exit position in evacuation process. Simulation results show that the proposed model can reproduce exactly the real evacuation process in stadium. Therefore, this method might be useful to assess public buildings design.

Dynamic Route Decision Model-based Multi-agent Evacuation Simulation - Case Study of Nagata Ward, Kobe

In this research, involving local people's concerns in the decision on the evacuation route, a dynamic route deci- sion model is proposed by explicitly considering group evacuation, landmarks & evacuation signs, and familiarity with the local environment. A spatial relationship-dependent approach is used to measure the difference in resi- dents regarding local knowledge. To understand the people's decision-making process for evacuation routes, a survey was conducted with members of the Zonta Club in Japan. Based on the survey, a prototype version of a multi-agent simulation (MAS) system is developed for the case area, Nagata Ward, Kobe.