Deep Reinforcement Learning for Sim-to-Real Robot Navigation with a Minimal Sensor Suite for Beach-Cleaning Applications

Autonomous beach-cleaning robots require reliable, low-cost navigation on sand. We study Sim-to-Real transfer of deep reinforcement learning (DRL) policies using a minimal sensor suite—wheel-encoder odometry and a single 2-D LiDAR—on a 30 kg differential-drive platform (Raspberry Pi 4). Two policies...

Descripció completa

Dades bibliogràfiques

Autors principals:	Guillermo Cid Ampuero, Gabriel Hermosilla, Germán Varas, Matías Toribio Clark
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2025-10-01
Col·lecció:	Applied Sciences
Matèries:	sim-to-real transfer deep reinforcement learning minimal sensor suite PPO-mask low-cost mobile robotics autonomous navigation
Accés en línia:	https://www.mdpi.com/2076-3417/15/19/10719
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!