{"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/semi-parametric-topological-memory-for","title":"Semi-parametric Topological Memory for Navigation","arxiv_id":"1803.00653","date":"2018-03-01","proceeding":"ICLR 2018 1","authors":["Nikolay Savinov","Alexey Dosovitskiy","Vladlen Koltun"],"abstract":"We introduce a new memory architecture for navigation in previously unseen\nenvironments, inspired by landmark-based navigation in animals. The proposed\nsemi-parametric topological memory (SPTM) consists of a (non-parametric) graph\nwith nodes corresponding to locations in the environment and a (parametric)\ndeep network capable of retrieving nodes from the graph based on observations.\nThe graph stores no metric information, only connectivity of locations\ncorresponding to the nodes. We use SPTM as a planning module in a navigation\nsystem. Given only 5 minutes of footage of a previously unseen maze, an\nSPTM-based navigation agent can build a topological map of the environment and\nuse it to confidently navigate towards goals. The average success rate of the\nSPTM agent in goal-directed navigation across test environments is higher than\nthe best-performing baseline by a factor of three. A video of the agent is\navailable at https://youtu.be/vRF7f4lhswo","url_abs":"http://arxiv.org/abs/1803.00653v1","url_pdf":"http://arxiv.org/pdf/1803.00653v1.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":"semi-parametric-topological-memory-for","repo_url":"https://github.com/nsavinov/SPTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.00653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00653"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nsavinov/SPTM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3a60ce0980fe5a66","entry":"load_array_from_hdf5","repo":"nsavinov/SPTM","repo_kind":"listed","path":"src/common/util.py","file_url":"https://github.com/nsavinov/SPTM/blob/HEAD/src/common/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a60ce0980fe5a66"}},{"code_sha256_prefix":"1eb55fc82e80bf58","entry":"mean","repo":"nsavinov/SPTM","repo_kind":"listed","path":"src/common/util.py","file_url":"https://github.com/nsavinov/SPTM/blob/HEAD/src/common/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1eb55fc82e80bf58"}},{"code_sha256_prefix":"58c8e30e91c0cb14","entry":"setup_training_paths","repo":"nsavinov/SPTM","repo_kind":"listed","path":"src/train/train_setup.py","file_url":"https://github.com/nsavinov/SPTM/blob/HEAD/src/train/train_setup.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58c8e30e91c0cb14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}