{"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/self-monitoring-navigation-agent-via","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","arxiv_id":"1901.03035","date":"2019-01-10","proceeding":"ICLR 2019 5","authors":["Chih-Yao Ma","Jiasen Lu","Zuxuan Wu","Ghassan AlRegib","Zsolt Kira","Richard Socher","Caiming Xiong"],"abstract":"The Vision-and-Language Navigation (VLN) task entails an agent following\nnavigational instruction in photo-realistic unknown environments. This\nchallenging task demands that the agent be aware of which instruction was\ncompleted, which instruction is needed next, which way to go, and its\nnavigation progress towards the goal. In this paper, we introduce a\nself-monitoring agent with two complementary components: (1) visual-textual\nco-grounding module to locate the instruction completed in the past, the\ninstruction required for the next action, and the next moving direction from\nsurrounding images and (2) progress monitor to ensure the grounded instruction\ncorrectly reflects the navigation progress. We test our self-monitoring agent\non a standard benchmark and analyze our proposed approach through a series of\nablation studies that elucidate the contributions of the primary components.\nUsing our proposed method, we set the new state of the art by a significant\nmargin (8% absolute increase in success rate on the unseen test set). Code is\navailable at https://github.com/chihyaoma/selfmonitoring-agent .","url_abs":"http://arxiv.org/abs/1901.03035v1","url_pdf":"http://arxiv.org/pdf/1901.03035v1.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":"self-monitoring-navigation-agent-via","repo_url":"https://github.com/chihyaoma/selfmonitoring-agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"self-monitoring-navigation-agent-via","repo_url":"https://github.com/ayusefi/Localization-Papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"},{"task_slug":"vision-language-navigation","task_name":"Vision-Language Navigation"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/vision-and-language-navigation-on-vln","task":"Vision and Language Navigation","dataset":"VLN Challenge","model":"Self-Monitoring Navigation Agent (no beam search; Progress Inference)","rank_in_archive_order":115,"of":145,"metrics":{"error":"5.67","length":"18.04","oracle success":"0.59","spl":"0.35","success":"0.48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.03035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.03035"}},"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/ayusefi/Localization-Papers","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chihyaoma/selfmonitoring-agent","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"91a412404a2ae592","entry":"build_mlp","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/models/modules.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/models/modules.py","link_basis":"first_harvest_node","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":"91a412404a2ae592"}},{"code_sha256_prefix":"19449a71349e2621","entry":"build_vocab","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/utils.py","link_basis":"first_harvest_node","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":"19449a71349e2621"}},{"code_sha256_prefix":"f3bcfc9ebf343e45","entry":"create_mask","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/models/modules.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/models/modules.py","link_basis":"first_harvest_node","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":"f3bcfc9ebf343e45"}},{"code_sha256_prefix":"be2e80a5268aabb2","entry":"load_datasets","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/utils.py","link_basis":"first_harvest_node","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":"be2e80a5268aabb2"}},{"code_sha256_prefix":"e3a90df1a875a38e","entry":"load_nav_graphs","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/utils.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/utils.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":"e3a90df1a875a38e"}},{"code_sha256_prefix":"37024446ae219cc6","entry":"proj_masking","repo":"chihyaoma/selfmonitoring-agent","repo_kind":"official","path":"tasks/R2R-pano/models/modules.py","file_url":"https://github.com/chihyaoma/selfmonitoring-agent/blob/HEAD/tasks/R2R-pano/models/modules.py","link_basis":"first_harvest_node","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":"37024446ae219cc6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}