{"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/generalization-through-simulation-integrating","title":"Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight","arxiv_id":"1902.03701","date":"2019-02-11","proceeding":null,"authors":["Katie Kang","Suneel Belkhale","Gregory Kahn","Pieter Abbeel","Sergey Levine"],"abstract":"Deep reinforcement learning provides a promising approach for vision-based\ncontrol of real-world robots. However, the generalization of such models\ndepends critically on the quantity and variety of data available for training.\nThis data can be difficult to obtain for some types of robotic systems, such as\nfragile, small-scale quadrotors. Simulated rendering and physics can provide\nfor much larger datasets, but such data is inherently of lower quality: many of\nthe phenomena that make the real-world autonomous flight problem challenging,\nsuch as complex physics and air currents, are modeled poorly or not at all, and\nthe systematic differences between simulation and the real world are typically\nimpossible to eliminate. In this work, we investigate how data from both\nsimulation and the real world can be combined in a hybrid deep reinforcement\nlearning algorithm. Our method uses real-world data to learn about the dynamics\nof the system, and simulated data to learn a generalizable perception system\nthat can enable the robot to avoid collisions using only a monocular camera. We\ndemonstrate our approach on a real-world nano aerial vehicle collision\navoidance task, showing that with only an hour of real-world data, the\nquadrotor can avoid collisions in new environments with various lighting\nconditions and geometry. Code, instructions for building the aerial vehicles,\nand videos of the experiments can be found at github.com/gkahn13/GtS","url_abs":"http://arxiv.org/abs/1902.03701v1","url_pdf":"http://arxiv.org/pdf/1902.03701v1.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":"generalization-through-simulation-integrating","repo_url":"https://github.com/gkahn13/GtS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"collision-avoidance","task_name":"Collision Avoidance"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.03701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.03701"}},"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/gkahn13/GtS","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"e671da62a014e6cf","entry":"bhat_label_func","repo":"gkahn13/GtS","repo_kind":"official","path":"configs/train_in_sim.py","file_url":"https://github.com/gkahn13/GtS/blob/HEAD/configs/train_in_sim.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":"e671da62a014e6cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}