Collaborative Decision-Making Method of Emergency Response for Highway Incidents

Abstract

With the continuous increase in highway mileage and vehicles in China, highway accidents are also increasing year by year. However, the on-site disposal procedures of highway accidents are complex, which makes it difficult for the emergency department to fully observe the accident scene, resulting in the lack of sufficient communication and cooperation between multiple emergency departments, making the rescue efficiency low and wasting valuable rescue time, and causing unnecessary injury or loss of life due to the lack of timely assistance. Thus, this paper proposes a multi-agent-based collaborative emergency-decision-making algorithm for traffic accident on-site disposal. Firstly, based on the analysis and abstraction of highway surveillance videos obtained from the Shaanxi Provincial Highway Administration, this paper constructs an emergency disposal model based on Petri net to simulate the emergency on-site disposal procedures. After transforming the emergency disposal model into a Markov game model and applying it to the multi-agent deep deterministic strategy gradient (MADDPG) algorithm proposed in this paper, the multiple agents can optimize the emergency-decision-making and on-site disposal procedures through interactive learning with the environment. Finally, the proposed algorithm is compared with the typical algorithm and the actual processing procedure in the simulation experiment of an actual Shaanxi highway traffic accident. The results show that the proposed emergency-decision-making method could greatly improve collaboration efficiency among emergency departments and effectively reduce emergency response time. This algorithm is not only superior to other decision-making algorithms such as genetic algorithm (EA), evolutionary strategy (ES), and deep Q network (DQN), but also reduces the disposal processes by 28%, 28%, and 42%, respectively, compared with the actual disposal process in three emergency disposal cases. In summary, with the continuous development of information technology and highway management systems, the multi-agent-based collaborative emergency-decision-making algorithm will contribute to the actual emergency response process and emergency disposal in the future, improving rescue efficiency and ensuring the safety of individuals. The on-site disposal procedure of freeway accidents is complicated, and the emergency response time is limited, which makes it difficult for emergency response departments to fully observe the accident scene, leading to the lack of sufficient communication and team cooperation among multiple emergency departments. This paper proposes a multi-agent-based collaborative emergency-decision-making algorithm for traffic accident on-site disposal. Firstly, through analyzing freeway surveillance videos obtained from the Shaanxi Provincial Freeway Administration, this paper constructs an emergency disposal model based on Petri net to simulate the emergency on-site disposal procedures. Then, an emergency-decision-making method based on a multi-agent deep deterministic policy gradient algorithm is proposed to optimize the emergency-decision-making and on-site disposal procedures. Finally, the proposed algorithm is compared with the typical algorithm in a simulation experiment of an actual Shaanxi freeway traffic accident, and the difference between the proposed algorithm and the actual processing procedure is also analyzed. The results show that the proposed emergency-decision-making method could greatly improve team collaboration efficiency among emergency departments and effectively reduce emergency response time. This algorithm is not only superior to other decision-making algorithms, but also reduces the disposal processes by 28%, 28%, and 42%, respectively, compared with the actual disposal process in the three studied cases. It is believed that the continuous development of information technology and freeway management systems will help to improve actual emergency response times and emergency drills in the future.

Research on lane-level intelligent control strategies under multi-lane failure scenarios

“…Existing traffic flow control measures include flow restriction control, speed coordination control, lane ramp management, queuing warning control, dynamic mixing control, dynamic information, path-inducing control, etc. [3][4][5]. In 2020, Lin Yi [6] aimed at the highway entrance ramp scenario based on the two control strategies of vehicle coordination control and ramp traffic flow control to improve the efficiency of roadway access and to ensure that the state of downstream traffic flow is In 2022, Li Qiaoru [7] proposed a highway merging zone traffic density optimization model for highway merging zone traffic efficiency and other issues, using a combination of variable speed limit and lane changing control measures, which can effectively use the cooperative control method, and has apparent improvements in road traffic efficiency and traffic safety.…”

Research on the evolutionary control of unsafe behavior of construction personnel based on multi-field coupled-homogeneous analysis model

“…Prior research has employed multi-agent technology to investigate engineering risks, including the identification of the main risk factors of shield tunnelling projects using a safety computational experiment system and the simulation of various risk control strategies for construction projects using a risk evolution model based on multi-agent modelling and stochastic methods [ 31 , 32 ]. Multi-agent-based collaborative emergency decision-making algorithms have also been proposed for emergency response to traffic accidents, and simulation modeling of human-machine-environment-related risk factors in coal mines has been conducted using multi-agent technology [ 33 , 34 ].…”

Advanced Meteorological Hazard Defense Capability Assessment: Addressing Sample Imbalance with Deep Learning Approaches

“…Innovative Studies and Technological Advancements: Recent studies have ventured deeper into the nuances of management strategies and institutional evolution. Junfeng Yao et al (2023) utilized network analysis and the Petri net model to foster organizational collaboration, concentrating on the synergy of emergency management entities and disaster response protocols, thereby enhancing efficiency and reducing response time [13]. On another front, Ling Shen et al (2023) leveraged a social networking perspective to amplify emergency management competencies, advocating for a collaborative governance mechanism involving multiple entities, particularly emphasizing grassroots governments [14].…”