Next Article in Journal
An Adaptive Embedding Network with Spatial Constraints for the Use of Few-Shot Learning in Endangered-Animal Detection
Previous Article in Journal
Geospatial Web Services Discovery through Semantic Annotation of WPS
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
IJGI
Volume 11
Issue 4
10.3390/ijgi11040255
ijgi-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

HDRLM3D: A Deep Reinforcement Learning-Based Model with Human-like Perceptron and Policy for Crowd Evacuation in 3D Environments

by
Dong Zhang
1,2,
Wenhang Li
1,*,
Jianhua Gong
1,2,3,
Lin Huang
1,
Guoyong Zhang
1,
Shen Shen
4,
Jiantao Liu
5 and
Haonan Ma
1,2
1
National Engineering Research Center for Geoinformatics, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2
University of Chinese Academy of Sciences, Beijing 100049, China
3
Zhejiang-CAS Application Center for Geoinformatics, Jiaxing 314199, China
4
State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China
5
School of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan 250101, China
*
Author to whom correspondence should be addressed.
ISPRS Int. J. Geo-Inf. 2022, 11(4), 255; https://doi.org/10.3390/ijgi11040255
Submission received: 28 February 2022 / Revised: 28 March 2022 / Accepted: 8 April 2022 / Published: 13 April 2022
Browse Figures
Versions Notes

Abstract

At present, a common drawback of crowd simulation models is that they are mainly simulated in (abstract) 2D environments, which limits the simulation of crowd behaviors observed in real 3D environments. Therefore, we propose a deep reinforcement learning-based model with human-like perceptron and policy for crowd evacuation in 3D environments (HDRLM3D). In HDRLM3D, we propose a vision-like ray perceptron (VLRP) and combine it with a redesigned global (or local) perceptron (GOLP) to form a human-like perception model. We propose a double-branch feature extraction and decision network (DBFED-Net) as the policy, which can extract features and make behavioral decisions. Moreover, we validate our method’s ability to reproduce typical phenomena and behaviors through experiments in two different scenarios. In scenario I, we reproduce the bottleneck effect of crowds and verify the effectiveness and advantages of HDRLM3D by comparing it with real crowd experiments and classical methods in terms of density maps, fundamental diagrams, and evacuation times. In scenario II, we reproduce agents’ navigation and obstacle avoidance behaviors and demonstrate the advantages of HDRLM3D for crowd simulation in unknown 3D environments by comparing it with other deep reinforcement learning-based models in terms of trajectories and numbers of collisions.
Keywords: crowd simulation; agent-based model; deep reinforcement learning; perceptron; policy crowd simulation; agent-based model; deep reinforcement learning; perceptron; policy

Share and Cite

MDPI and ACS Style

Zhang, D.; Li, W.; Gong, J.; Huang, L.; Zhang, G.; Shen, S.; Liu, J.; Ma, H. HDRLM3D: A Deep Reinforcement Learning-Based Model with Human-like Perceptron and Policy for Crowd Evacuation in 3D Environments. ISPRS Int. J. Geo-Inf. 2022, 11, 255. https://doi.org/10.3390/ijgi11040255

AMA Style

Zhang D, Li W, Gong J, Huang L, Zhang G, Shen S, Liu J, Ma H. HDRLM3D: A Deep Reinforcement Learning-Based Model with Human-like Perceptron and Policy for Crowd Evacuation in 3D Environments. ISPRS International Journal of Geo-Information. 2022; 11(4):255. https://doi.org/10.3390/ijgi11040255

Chicago/Turabian Style

Zhang, Dong, Wenhang Li, Jianhua Gong, Lin Huang, Guoyong Zhang, Shen Shen, Jiantao Liu, and Haonan Ma. 2022. "HDRLM3D: A Deep Reinforcement Learning-Based Model with Human-like Perceptron and Policy for Crowd Evacuation in 3D Environments" ISPRS International Journal of Geo-Information 11, no. 4: 255. https://doi.org/10.3390/ijgi11040255

APA Style

Zhang, D., Li, W., Gong, J., Huang, L., Zhang, G., Shen, S., Liu, J., & Ma, H. (2022). HDRLM3D: A Deep Reinforcement Learning-Based Model with Human-like Perceptron and Policy for Crowd Evacuation in 3D Environments. ISPRS International Journal of Geo-Information, 11(4), 255. https://doi.org/10.3390/ijgi11040255

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop