Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand
Efficient crowd evacuation from railway platforms is critical for passenger safety during emergencies. This study introduces a novel dynamic emergency evacuation route generator using the Proximal Policy Optimization (PPO) algorithm within a custom-built 3D simulation environment developed in Unity....
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10792441/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536191104548864 |
|---|---|
| author | Sushank Chaudhary Nitinun Sinpan Pruk Sasithong Sunita Khichar Panithan la-Aiddee Natt Leelawat Amir Parnianifard Suvit Poomrittigul Lunchakorn Wuttisittikulkij |
| author_facet | Sushank Chaudhary Nitinun Sinpan Pruk Sasithong Sunita Khichar Panithan la-Aiddee Natt Leelawat Amir Parnianifard Suvit Poomrittigul Lunchakorn Wuttisittikulkij |
| author_sort | Sushank Chaudhary |
| collection | DOAJ |
| description | Efficient crowd evacuation from railway platforms is critical for passenger safety during emergencies. This study introduces a novel dynamic emergency evacuation route generator using the Proximal Policy Optimization (PPO) algorithm within a custom-built 3D simulation environment developed in Unity. We independently created a detailed digital twin of Krung Thep Aphiwat Central Terminal, Thailand’s largest train station, and implemented all elements of the simulation, including the Social Force Model, to accurately replicate crowd behaviors and interactions during evacuation scenarios. Through extensive training over 3,000,000 episodes, our PPO-based model achieved significant improvements in evacuation efficiency. The results indicate that in a major emergency scenario, increasing the number of agents in the station reduced the number of remaining passengers from 111 to just 6, highlighting the model’s effectiveness. Similarly, in a minor emergency scenario, the average number of remaining passengers dropped from 38 to 1 with the addition of more agents. These findings confirm the model’s ability to adapt to different emergency conditions, offering a practical and scalable solution for enhancing evacuation strategies in high-density environments. Furthermore, increasing the agents’ sight range also improved evacuation efficiency, with a 20-meter sight range yielding the best results. |
| format | Article |
| id | doaj-art-8f600011f5914f23a5027ad35fee5325 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8f600011f5914f23a5027ad35fee53252025-01-15T00:01:25ZengIEEEIEEE Access2169-35362024-01-011219696919698310.1109/ACCESS.2024.351515310792441Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, ThailandSushank Chaudhary0https://orcid.org/0000-0002-1715-9689Nitinun Sinpan1Pruk Sasithong2https://orcid.org/0000-0001-9382-5404Sunita Khichar3https://orcid.org/0000-0002-5157-3461Panithan la-Aiddee4Natt Leelawat5https://orcid.org/0000-0001-5181-2584Amir Parnianifard6Suvit Poomrittigul7https://orcid.org/0000-0001-5565-4077Lunchakorn Wuttisittikulkij8https://orcid.org/0000-0002-3033-3020School of Computer, Guangdong University of Petrochemical Technology, Maoming, ChinaDepartment of Electrical Engineering, Wireless Communication Ecosystem Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Electrical Engineering, Wireless Communication Ecosystem Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Electrical Engineering, Wireless Communication Ecosystem Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Electrical Engineering, Wireless Communication Ecosystem Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandDepartment of Industrial Engineering, Disaster and Risk Management Information Systems Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandGlasgow College, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information Technology, King Mongkut’s Institute of Technology Ladkrabang (KMITL), Bangkok, ThailandDepartment of Electrical Engineering, Wireless Communication Ecosystem Research Unit, Faculty of Engineering, Chulalongkorn University, Bangkok, ThailandEfficient crowd evacuation from railway platforms is critical for passenger safety during emergencies. This study introduces a novel dynamic emergency evacuation route generator using the Proximal Policy Optimization (PPO) algorithm within a custom-built 3D simulation environment developed in Unity. We independently created a detailed digital twin of Krung Thep Aphiwat Central Terminal, Thailand’s largest train station, and implemented all elements of the simulation, including the Social Force Model, to accurately replicate crowd behaviors and interactions during evacuation scenarios. Through extensive training over 3,000,000 episodes, our PPO-based model achieved significant improvements in evacuation efficiency. The results indicate that in a major emergency scenario, increasing the number of agents in the station reduced the number of remaining passengers from 111 to just 6, highlighting the model’s effectiveness. Similarly, in a minor emergency scenario, the average number of remaining passengers dropped from 38 to 1 with the addition of more agents. These findings confirm the model’s ability to adapt to different emergency conditions, offering a practical and scalable solution for enhancing evacuation strategies in high-density environments. Furthermore, increasing the agents’ sight range also improved evacuation efficiency, with a 20-meter sight range yielding the best results.https://ieeexplore.ieee.org/document/10792441/Metaverseartificial intelligencecrowd evacuationproximal policy optimization |
| spellingShingle | Sushank Chaudhary Nitinun Sinpan Pruk Sasithong Sunita Khichar Panithan la-Aiddee Natt Leelawat Amir Parnianifard Suvit Poomrittigul Lunchakorn Wuttisittikulkij Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand IEEE Access Metaverse artificial intelligence crowd evacuation proximal policy optimization |
| title | Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand |
| title_full | Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand |
| title_fullStr | Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand |
| title_full_unstemmed | Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand |
| title_short | Proximal Policy Optimization for Crowd Evacuation in Complex Environments—A Metaverse Approach at Krung Thep Aphiwat Central Terminal, Thailand |
| title_sort | proximal policy optimization for crowd evacuation in complex environments x2014 a metaverse approach at krung thep aphiwat central terminal thailand |
| topic | Metaverse artificial intelligence crowd evacuation proximal policy optimization |
| url | https://ieeexplore.ieee.org/document/10792441/ |
| work_keys_str_mv | AT sushankchaudhary proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT nitinunsinpan proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT pruksasithong proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT sunitakhichar proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT panithanlaaiddee proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT nattleelawat proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT amirparnianifard proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT suvitpoomrittigul proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand AT lunchakornwuttisittikulkij proximalpolicyoptimizationforcrowdevacuationincomplexenvironmentsx2014ametaverseapproachatkrungthepaphiwatcentralterminalthailand |