Learning to Navigate in Cities Without a Map

by   Piotr Mirowski, et al.

Navigating through unstructured environments is a basic capability of intelligent creatures, and thus is of fundamental interest in the study and development of artificial intelligence. Long-range navigation is a complex cognitive task that relies on developing an internal representation of space, grounded by recognisable landmarks and robust visual processing, that can simultaneously support continuous self-localisation ("I am here") and a representation of the goal ("I am going there"). Building upon recent research that applies deep reinforcement learning to maze navigation problems, we present an end-to-end deep reinforcement learning approach that can be applied on a city scale. Recognising that successful navigation relies on integration of general policies with locale-specific knowledge, we propose a dual pathway architecture that allows locale-specific features to be encapsulated, while still enabling transfer to multiple cities. We present an interactive navigation environment that uses Google StreetView for its photographic content and worldwide coverage, and demonstrate that our learning method allows agents to learn to navigate multiple cities and to traverse to target destinations that may be kilometres away. A video summarizing our research and showing the trained agent in diverse city environments as well as on the transfer task is available at: goo.gl/ESUfho.


page 1

page 3


Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation

We present a robot navigation system that uses an imitation learning fra...

The StreetLearn Environment and Dataset

Navigation is a rich and well-grounded problem domain that drives progre...

Latent Space Reinforcement Learning for Steering Angle Prediction

Model-free reinforcement learning has recently been shown to successfull...

Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning

Navigation is a complex skill with a long history of research in animals...

A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment

In this work we use deep reinforcement learning to create an autonomous ...

Synthesized Policies for Transfer and Adaptation across Tasks and Environments

The ability to transfer in reinforcement learning is key towards buildin...

Please sign up or login with your details

Forgot password? Click here to reset