Deep deterministic policy gradient algorithm for crowd-evacuation path planning

•We propose E-MADDPG algorithm with higher learning efficiency based on MADDPG.•We extract the motion trajectory from the pedestrian video to reduce the state space.•We propose a hierarchical crowd evacuation path planning method based on DRL. In existing evacuation methods, the large number of pede...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computers & industrial engineering Jg. 161; S. 107621
Hauptverfasser:	Li, Xinjin, Liu, Hong, Li, Junqing, Li, Yan
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.11.2021
Schlagworte:	Crowd simulation for evacuation Deep reinforcement learning Multi-agent reinforcement learning Path planning Crowd simulation for evacuation Multi-agent reinforcement learning Deep reinforcement learning Path planning
ISSN:	0360-8352, 1879-0550
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!