Learning to Navigate in Cities Without a Map
Piotr Mirowski, Matthew Koichi Grimes, Mateusz Malinowski, Karl Moritz, Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Koray Kavukcuoglu,, Andrew Zisserman, Raia Hadsell

TL;DR
This paper introduces an end-to-end deep reinforcement learning approach for city-scale navigation using Google StreetView data, enabling agents to learn and transfer navigation skills across multiple urban environments.
Contribution
It proposes a dual pathway architecture that combines general policies with locale-specific features for scalable city navigation, and provides an interactive environment for training and testing.
Findings
Agents successfully navigate multiple cities.
Agents can reach destinations kilometers away.
Transfer learning enables city-to-city generalization.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Reinforcement Learning in Robotics · Human Mobility and Location-Based Analysis
MethodsAttention Model
