DeepNav: Learning to Navigate Large Cities
arXiv:1701.09135
Abstract
We present DeepNav, a Convolutional Neural Network (CNN) based algorithm for navigating large cities using locally visible street-view images. The DeepNav agent learns to reach its destination quickly by making the correct navigation decisions at intersections. We collect a large-scale dataset of street-view images organized in a graph where nodes are connected by roads. This dataset contains 10 city graphs and more than 1 million street-view images. We propose 3 supervised learning approaches for the navigation task and show how A* search in the city graph can be used to generate supervision for the learning. Our annotation process is fully automated using publicly available mapping services and requires no human input. We evaluate the proposed DeepNav models on 4 held-out cities for navigating to 5 different types of destinations. Our algorithms outperform previous work that uses hand-crafted features and Support Vector Regression (SVR)[19].
CVPR 2017 camera ready version
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Asynchronous Methods for Deep Reinforcement Learning
- PlaNet - Photo Geolocation with Convolutional Neural Networks
- Visual Saliency Based on Multiscale Deep Features
- Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning