{"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/gridmm-grid-memory-map-for-vision-and","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","arxiv_id":"2307.12907","date":"2023-07-24","proceeding":"ICCV 2023 1","authors":["Zihan Wang","Xiangyang Li","Jiahao Yang","Yeqi Liu","Shuqiang Jiang"],"abstract":"Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. To represent the previously visited environment, most approaches for VLN implement memory using recurrent states, topological maps, or top-down semantic maps. In contrast to these approaches, we build the top-down egocentric and dynamically growing Grid Memory Map (i.e., GridMM) to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better represent the spatial relations of the environment. From a local perspective, we further propose an instruction relevance aggregation method to capture fine-grained visual clues in each grid region. Extensive experiments are conducted on both the REVERIE, R2R, SOON datasets in the discrete environments, and the R2R-CE dataset in the continuous environments, showing the superiority of our proposed method.","url_abs":"https://arxiv.org/abs/2307.12907v4","url_pdf":"https://arxiv.org/pdf/2307.12907v4.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":"gridmm-grid-memory-map-for-vision-and","repo_url":"https://github.com/mrzihan/gridmm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.12907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12907"}},"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/mrzihan/gridmm","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MrZihan/GridMM","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_fixture":1,"ran_honours":1,"ran":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"c362aaed2935ceff","entry":"calc_position_distance","repo":"MrZihan/GridMM","repo_kind":"official","path":"map_nav_src/models/graph_utils.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/map_nav_src/models/graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c362aaed2935ceff"}},{"code_sha256_prefix":"168e35f8ed1ad0ce","entry":"calculate_vp_rel_pos_fts","repo":"MrZihan/GridMM","repo_kind":"official","path":"map_nav_src/models/graph_utils.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/map_nav_src/models/graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"168e35f8ed1ad0ce"}},{"code_sha256_prefix":"6d3a80fe9577452e","entry":"compute_accuracy_for_soft_targets","repo":"MrZihan/GridMM","repo_kind":"official","path":"pretrain_src/train_r2r.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/pretrain_src/train_r2r.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d3a80fe9577452e"}},{"code_sha256_prefix":"d60faa3e84e04846","entry":"get_angle_fts","repo":"MrZihan/GridMM","repo_kind":"official","path":"map_nav_src/models/graph_utils.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/map_nav_src/models/graph_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d60faa3e84e04846"}},{"code_sha256_prefix":"f46bad6811c75514","entry":"parse_with_config","repo":"MrZihan/GridMM","repo_kind":"official","path":"pretrain_src/parser.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/pretrain_src/parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f46bad6811c75514"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}