Using Reinforcement Learning to Iteratively Construct Road Networks from Satellite Images and GPS Data

Authors

  • Isaiah Gallardo Auburn University

DOI:

https://doi.org/10.1609/aaai.v38i21.30548

Keywords:

Map Inference, Road Network, GPS, Satellite Images

Abstract

Constructing road networks manually is a time consuming and labor-intensive process. This paper proposes a new method to iteratively construct road networks using reinforcement learning from a combined tensor-based representation of satellite image and GPS trajectory data.

Downloads

Published

2024-03-24

How to Cite

Gallardo, I. (2024). Using Reinforcement Learning to Iteratively Construct Road Networks from Satellite Images and GPS Data. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23740-23741. https://doi.org/10.1609/aaai.v38i21.30548