{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T03:51:31Z","timestamp":1769313091902,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T00:00:00Z","timestamp":1568937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61702023, No. 91538204"],"award-info":[{"award-number":["No. 61702023, No. 91538204"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,9,20]]},"DOI":"10.1145\/3366194.3366251","type":"proceedings-article","created":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T13:56:52Z","timestamp":1574258212000},"page":"324-329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Real-time obstacle avoidance with deep reinforcement learning Three-Dimensional Autonomous Obstacle Avoidance for UAV"],"prefix":"10.1145","author":[{"given":"Songyue","family":"Yang","sequence":"first","affiliation":[{"name":"School of Aeronautic Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Zhijun","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Aeronautic Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Xuzhi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}]},{"given":"Ronglei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Aeronautic Science and Engineering, Beihang University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,9,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Grau A. Optical flow based robot obstacle avoidance with matlab. Computer Vision.  Grau A. Optical flow based robot obstacle avoidance with matlab. Computer Vision."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302525"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980136"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"e_1_3_2_1_5_1","volume-title":"Appearance-based obstacle detection with monocular color vision. Aaai","author":"Ulrich I.","year":"2000","unstructured":"Ulrich , I. , & Nourbakhsh , I. R. ( 2000 ). Appearance-based obstacle detection with monocular color vision. Aaai . Ulrich, I., & Nourbakhsh, I. R. (2000). Appearance-based obstacle detection with monocular color vision. Aaai."},{"key":"e_1_3_2_1_6_1","volume-title":"Deep belief nets as function approximators for reinforcement learning","author":"Abtahi F.","year":"2011","unstructured":"Abtahi , F. , & Fasel , I. ( 2011 ). Deep belief nets as function approximators for reinforcement learning . Abtahi, F., & Fasel, I. (2011). Deep belief nets as function approximators for reinforcement learning."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.10.011"},{"key":"e_1_3_2_1_9_1","volume-title":"Neural fitted q iteration -- first experiences with a data efficient neural reinforcement learning method","author":"Riedmiller M.","year":"2005","unstructured":"Riedmiller , M. ( 2005 ). Neural fitted q iteration -- first experiences with a data efficient neural reinforcement learning method .. Riedmiller, M. (2005). Neural fitted q iteration -- first experiences with a data efficient neural reinforcement learning method.."},{"key":"e_1_3_2_1_10_1","volume-title":"International Joint Conference on Neural Networks.","author":"Lange S.","year":"2010","unstructured":"Lange , S. , & Riedmiller , M. ( 2010 ). Deep auto-encoder neural networks in reinforcement learning . International Joint Conference on Neural Networks. Lange, S., & Riedmiller, M. (2010). Deep auto-encoder neural networks in reinforcement learning. International Joint Conference on Neural Networks."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep reinforcement learning with double q-learning. Computer Science","author":"Van Hasselt H.","year":"2015","unstructured":"Van Hasselt , H. , Guez , A. , & Silver , D. ( 2015 ). Deep reinforcement learning with double q-learning. Computer Science . Van Hasselt, H., Guez, A., & Silver, D. (2015). Deep reinforcement learning with double q-learning. Computer Science."},{"key":"e_1_3_2_1_13_1","volume-title":"Dueling network architectures for deep reinforcement learning","author":"Wang Z.","year":"2015","unstructured":"Wang , Z. , Schaul , T. , Hessel , M. , Van Hasselt , H. , Lanctot , M. , & De Freitas , N. ( 2015 ). Dueling network architectures for deep reinforcement learning . Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., & De Freitas, N. (2015). Dueling network architectures for deep reinforcement learning."},{"key":"e_1_3_2_1_14_1","volume-title":"Prioritized experience replay. Computer Science","author":"Schaul T.","year":"2015","unstructured":"Schaul , T. , Quan , J. , Antonoglou , I. , & Silver , D. ( 2015 ). Prioritized experience replay. Computer Science . Schaul, T., Quan, J., Antonoglou, I., & Silver, D. (2015). Prioritized experience replay. Computer Science."},{"issue":"4","key":"e_1_3_2_1_15_1","first-page":"1","article-title":"Language understanding for text-based games using deep reinforcement learning","volume":"40","author":"Narasimhan K.","year":"2015","unstructured":"Narasimhan , K. , Kulkarni , T. , & Barzilay , R. ( 2015 ). Language understanding for text-based games using deep reinforcement learning . Computer Science , 40 ( 4 ), 1 -- 5 . Narasimhan, K., Kulkarni, T., & Barzilay, R. (2015). Language understanding for text-based games using deep reinforcement learning. Computer Science, 40(4), 1--5.","journal-title":"Computer Science"},{"key":"e_1_3_2_1_16_1","volume-title":"Deep recurrent q-learning for partially observable mdps. Computer Science","author":"Hausknecht M.","year":"2015","unstructured":"Hausknecht , M. , & Stone , P. ( 2015 ). Deep recurrent q-learning for partially observable mdps. Computer Science . Hausknecht, M., & Stone, P. (2015). Deep recurrent q-learning for partially observable mdps. Computer Science."},{"key":"e_1_3_2_1_17_1","volume-title":"Playing fps games with deep reinforcement learning","author":"Lample G.","year":"2016","unstructured":"Lample , G. , & Chaplot , D. S. ( 2016 ). Playing fps games with deep reinforcement learning . Lample, G., & Chaplot, D. S. (2016). Playing fps games with deep reinforcement learning."},{"key":"e_1_3_2_1_18_1","volume-title":"Vizdoom: drqn with prioritized experience replay, double-q learning, & snapshot ensembling","author":"Schulze C.","year":"2018","unstructured":"Schulze , C. , & Schulze , M. ( 2018 ). Vizdoom: drqn with prioritized experience replay, double-q learning, & snapshot ensembling . Schulze, C., & Schulze, M. (2018). Vizdoom: drqn with prioritized experience replay, double-q learning, & snapshot ensembling."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"e_1_3_2_1_20_1","volume-title":"Deep recurrent q-learning for partially observable mdps. Computer Science","author":"Hausknecht M.","year":"2015","unstructured":"Hausknecht , M. , & Stone , P. ( 2015 ). Deep recurrent q-learning for partially observable mdps. Computer Science . Hausknecht, M., & Stone, P. (2015). Deep recurrent q-learning for partially observable mdps. Computer Science."}],"event":{"name":"RICAI 2019: 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","location":"Shanghai China","acronym":"RICAI 2019"},"container-title":["Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366194.3366251","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3366194.3366251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:41Z","timestamp":1750202021000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3366194.3366251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,20]]},"references-count":20,"alternative-id":["10.1145\/3366194.3366251","10.1145\/3366194"],"URL":"https:\/\/doi.org\/10.1145\/3366194.3366251","relation":{},"subject":[],"published":{"date-parts":[[2019,9,20]]},"assertion":[{"value":"2019-09-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}