Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory

The role of robots in society keeps expanding, bringing with it the necessity of interacting and communicating with humans. In order to keep such interaction intuitive, we provide automatic wayfinding based on verbal navigational instructions. Our first contribution is the creation of a large-scale...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-10
Hauptverfasser:	Arun Balajee Vasudevan, Dai, Dengxin, Luc Van Gool
Format:	Artikel
Sprache:	eng
Schlagworte:	Anchors Annotations Autonomous navigation Cognition Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Robotics Datasets Landmarks Matching Neural networks Wayfinding
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!