{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:58:06Z","timestamp":1783789086845,"version":"3.55.0"},"reference-count":61,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"77","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2023,4,26]]},"abstract":"<jats:p>Autonomous robots can learn to perform visual navigation tasks from offline human demonstrations and generalize well to online and unseen scenarios within the same environment they have been trained on. It is challenging for these agents to take a step further and robustly generalize to new environments with drastic scenery changes that they have never encountered. Here, we present a method to create robust flight navigation agents that successfully perform vision-based fly-to-target tasks beyond their training environment under drastic distribution shifts. To this end, we designed an imitation learning framework using liquid neural networks, a brain-inspired class of continuous-time neural models that are causal and adapt to changing conditions. We observed that liquid agents learn to distill the task they are given from visual inputs and drop irrelevant features. Thus, their learned navigation skills transferred to new environments. When compared with several other state-of-the-art deep agents, experiments showed that this level of robustness in decision-making is exclusive to liquid networks, both in their differential equation and closed-form representations.<\/jats:p>","DOI":"10.1126\/scirobotics.adc8892","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T17:58:08Z","timestamp":1681927088000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":87,"title":["Robust flight navigation out of distribution with liquid neural networks"],"prefix":"10.1126","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6807-7042","authenticated-orcid":true,"given":"Makram","family":"Chahine","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9889-5222","authenticated-orcid":true,"given":"Ramin","family":"Hasani","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6968-6632","authenticated-orcid":true,"given":"Patrick","family":"Kao","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9407-091X","authenticated-orcid":true,"given":"Aaron","family":"Ray","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"Shubert","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6117-0076","authenticated-orcid":true,"given":"Mathias","family":"Lechner","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9673-1267","authenticated-orcid":true,"given":"Alexander","family":"Amini","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":true,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, MA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","unstructured":"Y. LeCun Y.\u00a0Bengio Reflections from the turing award winners in International Conference on Learning Representations (ICLR) (2020)."},{"key":"e_1_3_2_3_2","unstructured":"B. Neyshabur Z.\u00a0Li S.\u00a0Bhojanapalli Y.\u00a0LeCun N.\u00a0Srebro The role of over-parametrization in generalization of neural networks in 7th International Conference on Learning Representations ICLR 2019 (2019)."},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"V. Vapnik The Nature of Statistical Learning Theory (Springer science & business media 1999).","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"e_1_3_2_6_2","unstructured":"S. Ross G.\u00a0Gordon D.\u00a0Bagnell A reduction of imitation learning and structured prediction to no-regret online learning in Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (JMLR Workshop and Conference Proceedings 2011) pp.\u00a0627\u2013635."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"T. Zhang Z.\u00a0M.\u00a0Carthy O.\u00a0Jow D.\u00a0Lee X.\u00a0Chen K.\u00a0Goldberg P.\u00a0Abbeel Deep imitation learning for complex manipulation tasks from virtual reality teleoperation in 2018 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2018) pp.\u00a05628\u20135635.","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"e_1_3_2_8_2","unstructured":"E. Jang A.\u00a0Irpan M.\u00a0Khansari D.\u00a0Kappler F.\u00a0Ebert C.\u00a0Lynch S.\u00a0Levine C.\u00a0Finn Bc-z: Zero-shot task generalization with robotic imitation learning in Conference on Robot Learning (PMLR 2022) pp.\u00a0991\u20131002."},{"key":"e_1_3_2_9_2","unstructured":"P. Goyal R.\u00a0J.\u00a0Mooney S.\u00a0Niekum Zero-shot task adaptation using natural language. arXiv:2106.02972 [cs.AI] (5 June 2021)."},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"F. Codevilla M.\u00a0M\u00fc ller A.\u00a0L\u00f3pez V.\u00a0Koltun A.\u00a0Dosovitskiy End-to-end driving via conditional imitation learning in 2018 IEEE International Conference on Robotics and Automation (ICRA) (IEEE 2018) pp.\u00a04693\u20134700.","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"e_1_3_2_11_2","unstructured":"D. Ghosh A.\u00a0Gupta A.\u00a0Reddy J.\u00a0Fu C.\u00a0Devin B.\u00a0Eysenbach S.\u00a0Levine Learning to reach goals via iterated supervised learning in International Conference on Learning Representations (ICLR 2020)."},{"key":"e_1_3_2_12_2","unstructured":"C. Lynch M.\u00a0Khansari T.\u00a0Xiao V.\u00a0Kumar J.\u00a0Tompson S.\u00a0Levine P.\u00a0Sermanet Learning latent plans from play in Conference on Robot Learning (PMLR 2020) pp.\u00a01113\u20131132."},{"key":"e_1_3_2_13_2","unstructured":"S. Emmons B.\u00a0Eysenbach I.\u00a0Kostrikov S.\u00a0Levine Rvs: What is essential for offline rl via supervised learning? arXiv:2112.10751 [cs.LG] (20 December 2021)."},{"key":"e_1_3_2_14_2","unstructured":"R.\u00a0K.\u00a0Srivastava P.\u00a0Shyam F.\u00a0Mutz W.\u00a0Ja\u015bkowski J.\u00a0Schmidhuber Training agents using upside-down reinforcement learning. arXiv:1912.02877 [cs.LG] (5 December 2019)."},{"key":"e_1_3_2_15_2","unstructured":"G. Neumann J.\u00a0Peters Fitted q-iteration by advantage weighted regression in Advances in Neural Information Processing Systems (Curran Associates Inc. 2008) vol. 21."},{"key":"e_1_3_2_16_2","unstructured":"L. Chen K.\u00a0Lu A.\u00a0Rajeswaran K.\u00a0Lee A.\u00a0Grover M.\u00a0Laskin P.\u00a0Abbeel A.\u00a0Srinivas I.\u00a0Mordatch Decision transformer: Reinforcement learning via sequence modeling in Advances in Neural Information Processing Systems (2021) vol. 34."},{"key":"e_1_3_2_17_2","unstructured":"S. James M.\u00a0Bloesch A.\u00a0J.\u00a0Davison Task-embedded control networks for few-shot imitation learning in Conference on Robot Learning (PMLR 2018) pp.\u00a0783\u2013795."},{"key":"e_1_3_2_18_2","unstructured":"C. Finn T.\u00a0Yu T.\u00a0Zhang P.\u00a0Abbeel S.\u00a0Levine One-shot visual imitation learning via meta-learning Conference on Robot Learning (PMLR 2017) pp.\u00a0357\u2013368."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00237-3"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"M. Lechner R.\u00a0Hasani M.\u00a0Zimmer T.\u00a0A.\u00a0Henzinger R.\u00a0Grosu Designing worm inspired neural networks for interpretable robotic control in 2019 International Conference on Robotics and Automation (ICRA) (IEEE 2019) pp.\u00a087\u201394.","DOI":"10.1109\/ICRA.2019.8793840"},{"key":"e_1_3_2_21_2","unstructured":"R. Hasani M.\u00a0Lechner A.\u00a0Amini D.\u00a0Rus R.\u00a0Grosu A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits in International Conference on Machine Learning (PMLR 2020) pp.\u00a04082\u20134093."},{"key":"e_1_3_2_22_2","unstructured":"C. Vorbach R.\u00a0Hasani A.\u00a0Amini M.\u00a0Lechner D.\u00a0Rus Causal navigation by continuous-time neural networks in Advances in Neural Information Processing Systems (2021) vol. 34."},{"key":"e_1_3_2_23_2","unstructured":"A. Vaswani N.\u00a0Shazeer N.\u00a0Parmar J.\u00a0Uszkoreit L.\u00a0Jones A.\u00a0N.\u00a0Gomez L.\u00a0Kaiser I.\u00a0Polosukhin Attention is all you need in Advances in Neural Information Processing Systems (NIPS 2017) pp.\u00a05998\u20136008."},{"key":"e_1_3_2_24_2","unstructured":"S. Reed K.\u00a0Zolna E.\u00a0Parisotto S.\u00a0G.\u00a0Colmenarejo A.\u00a0Novikov G.\u00a0Barth-Maron M.\u00a0Gimenez Y.\u00a0Sulsky J.\u00a0Kay J.\u00a0T.\u00a0Springenberg T.\u00a0Eccles J.\u00a0Bruce A.\u00a0Razavi A.\u00a0Edwards N.\u00a0Heess Y.\u00a0Chen R.\u00a0Hadsell O.\u00a0Vinyals M.\u00a0Bordbar N.\u00a0de Freitas A generalist agent. arXiv:2205.06175 [cs.AI] (12 May 2022)."},{"key":"e_1_3_2_25_2","unstructured":"J. Kaplan S.\u00a0M.\u00a0Candlish T.\u00a0Henighan T.\u00a0B.\u00a0Brown B.\u00a0Chess R.\u00a0Child S.\u00a0Gray A.\u00a0Radford J.\u00a0Wu D.\u00a0Amodei Scaling laws for neural language models. arXiv:2001.08361 [cs.LG] (23 January 2020)."},{"key":"e_1_3_2_26_2","unstructured":"S. Bubeck M.\u00a0Sellke A universal law of robustness via isoperimetry in Advances in Neural Information Processing Systems (NeurIPS 2021) vol. 34."},{"key":"e_1_3_2_27_2","unstructured":"J. Hoffmann S.\u00a0Borgeaud A.\u00a0Mensch E.\u00a0Buchatskaya T.\u00a0Cai E.\u00a0Rutherford Diego de Las Casas L.\u00a0A.\u00a0Hendricks J.\u00a0Welbl A.\u00a0Clark T.\u00a0Hennigan E.\u00a0Noland K.\u00a0Millican G.\u00a0van den Driessche B.\u00a0Damoc A.\u00a0Guy S.\u00a0Osindero K.\u00a0Simonyan E.\u00a0Elsen J.\u00a0W.\u00a0Rae O.\u00a0Vinyals L.\u00a0Sifre Training compute-optimal large language models. arXiv:2203.15556 [cs.CL] (29 March 2022)."},{"key":"e_1_3_2_28_2","unstructured":"T. Brown B.\u00a0Mann N.\u00a0Ryder M.\u00a0Subbiah J.\u00a0D.\u00a0Kaplan P.\u00a0Dhariwal A.\u00a0Neelakantan P.\u00a0Shyam G.\u00a0Sastry A.\u00a0Askell S.\u00a0Agarwal A.\u00a0Herbert-Voss G.\u00a0Krueger T.\u00a0Henighan R.\u00a0Child A.\u00a0Ramesh D.\u00a0Ziegler J.\u00a0Wu C.\u00a0Winter C.\u00a0Hesse M.\u00a0Chen E.\u00a0Sigler M.\u00a0Litwin S.\u00a0Gray B.\u00a0Chess J.\u00a0Clark C.\u00a0Berner S.\u00a0M.\u00a0Candlish A.\u00a0Radford I.\u00a0Sutskever D.\u00a0Amodei Language models are few-shot learners in Advances in Neural Information Processing Systems (NeurIPS 2020) vol. 33 p.\u00a01877."},{"key":"e_1_3_2_29_2","unstructured":"V. Sanh A.\u00a0Webson C.\u00a0Raffel S.\u00a0Bach L.\u00a0Sutawika Z.\u00a0Alyafeai A.\u00a0Chaffin A.\u00a0Stiegler A.\u00a0Raja M.\u00a0Dey M Saiful Bari C.\u00a0Xu U.\u00a0Thakker S.\u00a0S.\u00a0Sharma E.\u00a0Szczechla T.\u00a0Kim G.\u00a0Chhablani N.\u00a0Nayak D.\u00a0Datta J.\u00a0Chang Mike Tian-Jian Jiang H.\u00a0Wang M.\u00a0Manica S.\u00a0Shen Z.\u00a0X.\u00a0Yong H.\u00a0Pandey R.\u00a0Bawden T.\u00a0Wang T.\u00a0Neeraj J.\u00a0Rozen A.\u00a0Sharma A.\u00a0Santilli T.\u00a0Fevry J.\u00a0A.\u00a0Fries R.\u00a0Teehan T.\u00a0L.\u00a0Scao S.\u00a0Biderman L.\u00a0Gao T.\u00a0Wolf A.\u00a0M.\u00a0Rush Multitask prompted training enables zero-shot task generalization in The Tenth International Conference on Learning Representations (ICLR 2022)."},{"key":"e_1_3_2_30_2","unstructured":"J. Wei M.\u00a0Bosma V.\u00a0Y.\u00a0Zhao K.\u00a0Guu A.\u00a0W.\u00a0Yu B.\u00a0Lester N.\u00a0Du A.\u00a0M.\u00a0Dai Q.\u00a0V.\u00a0Le Finetuned language models are zero-shot learners. arXiv:2109.01652 [cs.CL] (3 Sep 2021)."},{"key":"e_1_3_2_31_2","unstructured":"C. Jia Y.\u00a0Yang Y.\u00a0Xia Y.-T. Chen Z.\u00a0Parekh H.\u00a0Pham Q.\u00a0V.\u00a0Le Y.\u00a0Sung Z.\u00a0Li T.\u00a0Duerig Scaling up visual and vision-language representation learning with noisy text supervision in International Conference on Machine Learning (PMLR 2021) pp.\u00a04904\u20134916."},{"key":"e_1_3_2_32_2","unstructured":"J.-B. Alayrac J.\u00a0Donahue P.\u00a0Luc A.\u00a0Miech I.\u00a0Barr Y.\u00a0Hasson K.\u00a0Lenc A.\u00a0Mensch K.\u00a0Millican M.\u00a0Reynolds R.\u00a0Ring E.\u00a0Rutherford S.\u00a0Cabi T.\u00a0Han Z.\u00a0Gong S.\u00a0Samangooei M.\u00a0Monteiro J.\u00a0Menick S.\u00a0Borgeaud A.\u00a0Brock A.\u00a0Nematzadeh S.\u00a0Sharifzadeh M.\u00a0Binkowski R.\u00a0Barreira O.\u00a0Vinyals A.\u00a0Zisserman K.\u00a0Simonyan Flamingo: A visual language model for few-shot learning. arXiv:2204.14198 [cs.CV] (29 April 2022)."},{"key":"e_1_3_2_33_2","unstructured":"A. Ramesh P.\u00a0Dhariwal A.\u00a0Nichol C.\u00a0Chu M.\u00a0Chen Hierarchical text-conditional image generation with clip latents. arXiv:2204.06125 [cs.CV] (13 April 2022)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"J. Zhang K.\u00a0Yang C.\u00a0Ma S.\u00a0Rei\u00df K.\u00a0Peng R.\u00a0Stiefelhagen Bending reality: Distortion-aware transformers for adapting to panoramic semantic segmentation in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2022) pp.\u00a016917\u201316927.","DOI":"10.1109\/CVPR52688.2022.01641"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"A. Prakash K.\u00a0Chitta A.\u00a0Geiger Multi-modal fusion transformer for end-to-end autonomous driving in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2021) pp.\u00a07077\u20137087.","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"R. Hasani M.\u00a0Lechner A.\u00a0Amini D.\u00a0Rus R.\u00a0Grosu Liquid time constant networks in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2021) vol. 35 p.\u00a07657.","DOI":"10.1609\/aaai.v35i9.16936"},{"key":"e_1_3_2_37_2","unstructured":"B. Sch\u00f6lkopf Causality for machine learning. arXiv:1911.10500 [cs.LG] (24 Nov 2019)."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_39_2","unstructured":"Y. Rubanova R.\u00a0T.\u00a0Chen D.\u00a0K.\u00a0Duvenaud Latent ordinary differential equations for irregularly-sampled time series in Advances in Neural Information Processing Systems (NeurIPS 2019) vol. 32."},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","unstructured":"K. Cho B.\u00a0Van Merri\u00ebnboer D.\u00a0Bahdanau Y.\u00a0Bengio On the properties of neural machine translation: Encoder-decoder approaches. arXiv:1409.1259 (3 Sep 2014).","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"C. Lea R.\u00a0Vidal A.\u00a0Reiter G.\u00a0D.\u00a0Hager Temporal convolutional networks: A unified approach to action segmentation in European Conference on Computer Vision (Springer 2016) pp.\u00a047\u201354.","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"e_1_3_2_42_2","unstructured":"R.\u00a0T.\u00a0Chen Y.\u00a0Rubanova J.\u00a0Bettencourt D.\u00a0Duvenaud Neural ordinary differential equations in Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS 2018) pp.\u00a06572\u20136583."},{"key":"e_1_3_2_43_2","unstructured":"S. Bai J.\u00a0Z.\u00a0Kolter V.\u00a0Koltun An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271 [cs.LG] (4 Mar 2018)."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(03)00202-7"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"M. Bojarski A.\u00a0Choromanska K.\u00a0Choromanski B.\u00a0Firner L.\u00a0J.\u00a0Ackel U.\u00a0Muller P.\u00a0Yeres K.\u00a0Zieba Visualbackprop: Efficient visualization of cnns for autonomous driving in IEEE International Conference on Robotics and Automation (ICRA) (ICRA 2018) pp.\u00a01\u20138.","DOI":"10.1109\/ICRA.2018.8461053"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2005.1642"},{"key":"e_1_3_2_48_2","unstructured":"C. Koch I.\u00a0Segev Methods in Neuronal Modeling: From Ions to Networks (MIT Press 1998)."},{"key":"e_1_3_2_49_2","unstructured":"E.\u00a0R.\u00a0Kandel J.\u00a0H.\u00a0Schwartz T.\u00a0M.\u00a0Jessell Principles of Neural Science (McGraw-Hill 2000) vol. 4."},{"key":"e_1_3_2_50_2","first-page":"620","article-title":"Recherches quantitatives sur l\u2019excitation electrique des nerfs traitee comme une polarization","volume":"9","author":"Lapique L.","year":"1907","unstructured":"L.\u00a0Lapique,Recherches quantitatives sur l\u2019excitation electrique des nerfs traitee comme une polarization. J. Physiol. Pathol. 9, 620 (1907).","journal-title":"J. Physiol. Pathol."},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"R. Hasani M.\u00a0Lechner A.\u00a0Amini L.\u00a0Liebenwein A.\u00a0Ray M.\u00a0Tschaikowski G.\u00a0Teschl D.\u00a0Rus Closed-form continuous-time neural models. arXiv:2106.13898 [cs.LG] (25 June 2021).","DOI":"10.1038\/s42256-022-00556-7"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2017.0382"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1000033"},{"key":"e_1_3_2_54_2","unstructured":"J. Bergstra R.\u00a0Bardenet Y.\u00a0Bengio B.\u00a0K\u00e9gl Algorithms for hyper-parameter optimization in Advances in Neural Information Processing Systems (NIPS 2011) vol. 24."},{"key":"e_1_3_2_55_2","unstructured":"J. Bergstra D.\u00a0Yamins D.\u00a0Cox Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures in International Conference on Machine Learning (PMLR 2013) pp.\u00a0115\u2013123."},{"key":"e_1_3_2_56_2","unstructured":"Stanford Artificial Intelligence Laboratory et\u00a0al. Robotic operating system."},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","unstructured":"M. Bojarski A.\u00a0Choromanska K.\u00a0Choromanski B.\u00a0Firner L.\u00a0Jackel U.\u00a0Muller K.\u00a0Zieba Visualbackprop: efficient visualization of CNNs. arXiv:1611.05418 [cs.CV] (16 November 2017).","DOI":"10.1109\/ICRA.2018.8461053"},{"key":"e_1_3_2_58_2","unstructured":"S. Ross D.\u00a0Bagnell Efficient reductions for imitation learning in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (JMLR Workshop and Conference Proceedings 2010) pp.\u00a0661\u2013668."},{"key":"e_1_3_2_59_2","unstructured":"R.\u00a0S.\u00a0Sutton A.\u00a0G.\u00a0Barto Reinforcement Learning: An Introduction (MIT press 2018)."},{"key":"e_1_3_2_60_2","doi-asserted-by":"crossref","unstructured":"J. Chen B.\u00a0Yuan M.\u00a0Tomizuka Deep imitation learning for autonomous driving in generic urban scenarios with enhanced safety in 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2019) pp.\u00a02884\u20132890.","DOI":"10.1109\/IROS40897.2019.8968225"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","unstructured":"X. Li P.\u00a0Ye J.\u00a0Jin F.\u00a0Zhu F.-Y. Wang Data augmented deep behavioral cloning for urban traffic control operations under a parallel learning framework in IEEE Transactions on Intelligent Transportation Systems (IEEE 2021).","DOI":"10.1109\/TITS.2020.3048151"},{"key":"e_1_3_2_62_2","doi-asserted-by":"crossref","unstructured":"A. Amini T.-H. Wang I.\u00a0Gilitschenski W.\u00a0Schwarting Z.\u00a0Liu S.\u00a0Han S.\u00a0Karaman D.\u00a0Rus Vista 2.0: An open data-driven simulator for multimodal sensing and policy learning for autonomous vehicles. arXiv:2111.12083 [cs.RO] (23 November 2021).","DOI":"10.1109\/ICRA46639.2022.9812276"}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adc8892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T11:52:19Z","timestamp":1705405939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adc8892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,26]]},"references-count":61,"journal-issue":{"issue":"77","published-print":{"date-parts":[[2023,4,26]]}},"alternative-id":["10.1126\/scirobotics.adc8892"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adc8892","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,26]]},"assertion":[{"value":"2022-05-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadc8892"}}