Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data

Autonomous driving is complex, requiring sophisticated 3D scene understanding, localization, mapping, and control. Rather than explicitly modelling and fusing each of these components, we instead consider an end-to-end approach via reinforcement learning (RL). However, collecting exploration driving...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-10
Hauptverfasser:	So, John, Xie, Amber, Jung, Sunggoo, Edlund, Jeffrey, Thakker, Rohan, Agha-mohammadi, Ali, Abbeel, Pieter, James, Stephen
Format:	Artikel
Sprache:	eng
Schlagworte:	Image segmentation Learning Scene analysis Simulation
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!