{"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-map-natural-language-instructions","title":"Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight","arxiv_id":"1910.09664","date":"2019-10-21","proceeding":null,"authors":["Valts Blukis","Yannick Terme","Eyvind Niklasson","Ross A. Knepper","Yoav Artzi"],"abstract":"We propose a joint simulation and real-world learning framework for mapping navigation instructions and raw first-person observations to continuous control. Our model estimates the need for environment exploration, predicts the likelihood of visiting environment positions during execution, and controls the agent to both explore and visit high-likelihood positions. We introduce Supervised Reinforcement Asynchronous Learning (SuReAL). Learning uses both simulation and real environments without requiring autonomous flight in the physical environment during training, and combines supervised learning for predicting positions to visit and reinforcement learning for continuous control. We evaluate our approach on a natural language instruction-following task with a physical quadcopter, and demonstrate effective execution and exploration behavior.","url_abs":"https://arxiv.org/abs/1910.09664v1","url_pdf":"https://arxiv.org/pdf/1910.09664v1.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-map-natural-language-instructions","repo_url":"https://github.com/lil-lab/drif","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.09664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09664"}},"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/lil-lab/drif","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"56352a07778ba6d9","entry":"epoch_rl_filename","repo":"lil-lab/drif","repo_kind":"official","path":"mains/train/train_sureal.py","file_url":"https://github.com/lil-lab/drif/blob/HEAD/mains/train/train_sureal.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56352a07778ba6d9"}},{"code_sha256_prefix":"052eded449009a2f","entry":"epoch_sup_filename","repo":"lil-lab/drif","repo_kind":"official","path":"mains/train/train_sureal.py","file_url":"https://github.com/lil-lab/drif/blob/HEAD/mains/train/train_sureal.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"052eded449009a2f"}},{"code_sha256_prefix":"8cb9d5c31b81c78c","entry":"receive_stage1_state","repo":"lil-lab/drif","repo_kind":"official","path":"mains/train/train_sureal.py","file_url":"https://github.com/lil-lab/drif/blob/HEAD/mains/train/train_sureal.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8cb9d5c31b81c78c"}},{"code_sha256_prefix":"a485fdef0d69b6cf","entry":"query_user_load_discard","repo":"lil-lab/drif","repo_kind":"official","path":"mains/eval/evaluate.py","file_url":"https://github.com/lil-lab/drif/blob/HEAD/mains/eval/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a485fdef0d69b6cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}