Visual Target-Driven Robot Crowd Navigation with Limited FOV Using Self-Attention Enhanced Deep Reinforcement Learning

Navigating crowded environments poses significant challenges for mobile robots, particularly as traditional Simultaneous Localization and Mapping (SLAM)-based methods often struggle with dynamic and unpredictable settings. This paper proposes a visual target-driven navigation method using self-atten...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Yinbei Li, Qingyang Lyu, Jiaqiang Yang, Yasir Salam, Baixiang Wang
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	MDPI AG 2025-01-01
Serie:	Sensors
Ämnen:	crowd navigation deep reinforcement learning mapless navigation twin-delayed deep deterministic policy gradient (TD3)
Länkar:	https://www.mdpi.com/1424-8220/25/3/639
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!