Back to Search
Start Over
Transformer-based Localization from Embodied Dialog with Large-scale Pre-training
- Publication Year :
- 2022
- Publisher :
- arXiv, 2022.
-
Abstract
- We address the challenging task of Localization via Embodied Dialog (LED). Given a dialog from two agents, an Observer navigating through an unknown environment and a Locator who is attempting to identify the Observer's location, the goal is to predict the Observer's final location in a map. We develop a novel LED-Bert architecture and present an effective pretraining strategy. We show that a graph-based scene representation is more effective than the top-down 2D maps used in prior works. Our approach outperforms previous baselines.
- Subjects :
- FOS: Computer and information sciences
Computer Science - Computation and Language
Artificial Intelligence (cs.AI)
Computer Science - Artificial Intelligence
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Computation and Language (cs.CL)
Subjects
Details
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....22e01d38707dfb1fba2b620d87eef68c
- Full Text :
- https://doi.org/10.48550/arxiv.2210.04864