{"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/saynav-grounding-large-language-models-for","title":"SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments","arxiv_id":"2309.04077","date":"2023-09-08","proceeding":null,"authors":["Abhinav Rajvanshi","Karan Sikka","Xiao Lin","Bhoram Lee","Han-Pang Chiu","Alvaro Velasquez"],"abstract":"Semantic reasoning and dynamic planning capabilities are crucial for an autonomous agent to perform complex navigation tasks in unknown environments. It requires a large amount of common-sense knowledge, that humans possess, to succeed in these tasks. We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments. SayNav uses a novel grounding mechanism, that incrementally builds a 3D scene graph of the explored environment as inputs to LLMs, for generating feasible and contextually appropriate high-level plans for navigation. The LLM-generated plan is then executed by a pre-trained low-level planner, that treats each planned step as a short-distance point-goal navigation sub-task. SayNav dynamically generates step-by-step instructions during navigation and continuously refines future steps based on newly perceived information. We evaluate SayNav on multi-object navigation (MultiON) task, that requires the agent to utilize a massive amount of human knowledge to efficiently search multiple different objects in an unknown environment. We also introduce a benchmark dataset for MultiON task employing ProcTHOR framework that provides large photo-realistic indoor environments with variety of objects. SayNav achieves state-of-the-art results and even outperforms an oracle based baseline with strong ground-truth assumptions by more than 8% in terms of success rate, highlighting its ability to generate dynamic plans for successfully locating objects in large-scale new environments. The code, benchmark dataset and demonstration videos are accessible at https://www.sri.com/ics/computer-vision/saynav.","url_abs":"https://arxiv.org/abs/2309.04077v4","url_pdf":"https://arxiv.org/pdf/2309.04077v4.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":"saynav-grounding-large-language-models-for","repo_url":"https://github.com/arajv/SayNav","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"navigate","task_name":"Navigate"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.04077","atlas_url":"https://app.syntology.ai/?focus=2309.04077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.04077"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/arajv/SayNav","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":11},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":11,"samples":[{"code_sha256_prefix":"ef1c76d9e08018bb","entry":"check_if_plan_needed","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/pipeline.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ef1c76d9e08018bb"}},{"code_sha256_prefix":"06f0d3cd6eca4815","entry":"choose_random_door","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/hl_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/hl_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"06f0d3cd6eca4815"}},{"code_sha256_prefix":"fb4c28e1e7d5b6f6","entry":"construct_goal","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/llm.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/llm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fb4c28e1e7d5b6f6"}},{"code_sha256_prefix":"fab4fadbda28248c","entry":"extract_info","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/pointnav_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/pointnav_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fab4fadbda28248c"}},{"code_sha256_prefix":"847251abb9e81cf3","entry":"extract_obs_pointnav","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/pointnav_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/pointnav_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"847251abb9e81cf3"}},{"code_sha256_prefix":"0aeca4a755dab63c","entry":"extract_room_polygons","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/utils_scenegraph.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/utils_scenegraph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0aeca4a755dab63c"}},{"code_sha256_prefix":"35415fc333c3dff2","entry":"is_point_inside_room","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/hl_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/hl_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"35415fc333c3dff2"}},{"code_sha256_prefix":"9f619a3b774fa234","entry":"locate_in_room","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/utils_scenegraph.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/utils_scenegraph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9f619a3b774fa234"}},{"code_sha256_prefix":"cd88ae5b84779a10","entry":"objectID_to_roomID","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/utils_scenegraph.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/utils_scenegraph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cd88ae5b84779a10"}},{"code_sha256_prefix":"a0bb73f8c6dafbf4","entry":"snap","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/pointnav_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/pointnav_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a0bb73f8c6dafbf4"}},{"code_sha256_prefix":"bf2bb65701e00832","entry":"update_visited_doors","repo":"arajv/SayNav","repo_kind":"official","path":"src/python/hl_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/hl_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bf2bb65701e00832"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}