{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-navigate-in-cities-without-a-map","title":"Learning to Navigate in Cities Without a Map","arxiv_id":"1804.00168","date":"2018-03-31","proceeding":"NeurIPS 2018 12","authors":["Piotr Mirowski","Matthew Koichi Grimes","Mateusz Malinowski","Karl Moritz Hermann","Keith Anderson","Denis Teplyashin","Karen Simonyan","Koray Kavukcuoglu","Andrew Zisserman","Raia Hadsell"],"abstract":"Navigating through unstructured environments is a basic capability of\nintelligent creatures, and thus is of fundamental interest in the study and\ndevelopment of artificial intelligence. Long-range navigation is a complex\ncognitive task that relies on developing an internal representation of space,\ngrounded by recognisable landmarks and robust visual processing, that can\nsimultaneously support continuous self-localisation (\"I am here\") and a\nrepresentation of the goal (\"I am going there\"). Building upon recent research\nthat applies deep reinforcement learning to maze navigation problems, we\npresent an end-to-end deep reinforcement learning approach that can be applied\non a city scale. Recognising that successful navigation relies on integration\nof general policies with locale-specific knowledge, we propose a dual pathway\narchitecture that allows locale-specific features to be encapsulated, while\nstill enabling transfer to multiple cities. We present an interactive\nnavigation environment that uses Google StreetView for its photographic content\nand worldwide coverage, and demonstrate that our learning method allows agents\nto learn to navigate multiple cities and to traverse to target destinations\nthat may be kilometres away. The project webpage http://streetlearn.cc contains\na video summarising our research and showing the trained agent in diverse city\nenvironments and on the transfer task, the form to request the StreetLearn\ndataset and links to further resources. The StreetLearn environment code is\navailable at https://github.com/deepmind/streetlearn","url_abs":"http://arxiv.org/abs/1804.00168v3","url_pdf":"http://arxiv.org/pdf/1804.00168v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-navigate-in-cities-without-a-map","repo_url":"https://github.com/deepmind/streetlearn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-to-navigate-in-cities-without-a-map","repo_url":"https://github.com/google-deepmind/scalable_agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-navigate-in-cities-without-a-map","repo_url":"https://github.com/heiner/scalable_agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-to-navigate-in-cities-without-a-map","repo_url":"https://github.com/xiexiexiaoxiexie/Udacity-self-driving-car-engineer-P7-Highway-Driving","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-navigation","task_name":"Autonomous Navigation"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"am","method_name":"AM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00168","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}