{"citation":{"ieee":"C. J. Vorbach, R. Hasani, A. Amini, M. Lechner, and D. Rus, “Causal navigation by continuous-time neural networks,” in <i>35th Conference on Neural Information Processing Systems</i>, Virtual, 2021.","mla":"Vorbach, Charles J., et al. “Causal Navigation by Continuous-Time Neural Networks.” <i>35th Conference on Neural Information Processing Systems</i>, 2021.","short":"C.J. Vorbach, R. Hasani, A. Amini, M. Lechner, D. Rus, in:, 35th Conference on Neural Information Processing Systems, 2021.","ama":"Vorbach CJ, Hasani R, Amini A, Lechner M, Rus D. Causal navigation by continuous-time neural networks. In: <i>35th Conference on Neural Information Processing Systems</i>. ; 2021.","chicago":"Vorbach, Charles J, Ramin Hasani, Alexander Amini, Mathias Lechner, and Daniela Rus. “Causal Navigation by Continuous-Time Neural Networks.” In <i>35th Conference on Neural Information Processing Systems</i>, 2021.","ista":"Vorbach CJ, Hasani R, Amini A, Lechner M, Rus D. 2021. Causal navigation by continuous-time neural networks. 35th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems,  Advances in Neural Information Processing Systems, .","apa":"Vorbach, C. J., Hasani, R., Amini, A., Lechner, M., &#38; Rus, D. (2021). Causal navigation by continuous-time neural networks. In <i>35th Conference on Neural Information Processing Systems</i>. Virtual."},"conference":{"start_date":"2021-12-06","name":"NeurIPS: Neural Information Processing Systems","location":"Virtual","end_date":"2021-12-10"},"_id":"10670","language":[{"iso":"eng"}],"publication":"35th Conference on Neural Information Processing Systems","has_accepted_license":"1","author":[{"first_name":"Charles J","last_name":"Vorbach","full_name":"Vorbach, Charles J"},{"last_name":"Hasani","first_name":"Ramin","full_name":"Hasani, Ramin"},{"full_name":"Amini, Alexander","last_name":"Amini","first_name":"Alexander"},{"last_name":"Lechner","first_name":"Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias"},{"last_name":"Rus","first_name":"Daniela","full_name":"Rus, Daniela"}],"external_id":{"arxiv":["2106.08314"]},"file_date_updated":"2022-01-26T07:37:24Z","acknowledgement":"C.V., R.H. A.A. and D.R. are partially supported by Boeing and MIT. A.A. is supported by the National Science Foundation (NSF) Graduate Research Fellowship Program. M.L. is supported in part by the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award). Research was sponsored by the United States Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-1000. The views and conclusions contained in this document are those of the authors\r\nand should not be interpreted as representing the official policies, either expressed or implied, of the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.\r\n","project":[{"call_identifier":"FWF","name":"The Wittgenstein Prize","_id":"25F42A32-B435-11E9-9278-68D0E5697425","grant_number":"Z211"}],"ddc":["000"],"year":"2021","publication_status":"published","date_published":"2021-12-01T00:00:00Z","department":[{"_id":"GradSch"},{"_id":"ToHe"}],"abstract":[{"text":"Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to domain shifts by failing to account for the causal relationships between the agent and the environment. In this paper, we propose a theoretical and experimental framework for learning causal representations using continuous-time neural networks, specifically over their discrete-time counterparts. We evaluate our method in the context of visual-control learning of drones over a series of complex tasks, ranging from short- and long-term navigation, to chasing static and dynamic objects through photorealistic environments. Our results demonstrate that causal continuous-time\r\ndeep models can perform robust navigation tasks, where advanced recurrent models fail. These models learn complex causal control representations directly from raw visual inputs and scale to solve a variety of tasks using imitation learning.","lang":"eng"}],"main_file_link":[{"open_access":"1","url":"https://proceedings.neurips.cc/paper/2021/hash/67ba02d73c54f0b83c05507b7fb7267f-Abstract.html"}],"type":"conference","license":"https://creativecommons.org/licenses/by-nc-nd/3.0/","file":[{"access_level":"open_access","creator":"mlechner","file_name":"NeurIPS-2021-causal-navigation-by-continuous-time-neural-networks-Paper.pdf","content_type":"application/pdf","checksum":"be81f0ade174a8c9b2d4fe09590b2021","relation":"main_file","date_created":"2022-01-26T07:37:24Z","file_size":6841228,"success":1,"file_id":"10679","date_updated":"2022-01-26T07:37:24Z"}],"day":"01","month":"12","article_processing_charge":"No","date_updated":"2022-01-26T14:33:31Z","tmp":{"short":"CC BY-NC-ND (3.0)","image":"/images/cc_by_nc_nd.png","name":"Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode"},"quality_controlled":"1","title":"Causal navigation by continuous-time neural networks","status":"public","alternative_title":[" Advances in Neural Information Processing Systems"],"oa_version":"Published Version","oa":1,"user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","date_created":"2022-01-25T15:47:50Z"}