{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:51:15Z","timestamp":1776783075166,"version":"3.51.2"},"reference-count":46,"publisher":"Informa UK Limited","issue":"21-22","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Advanced Robotics"],"published-print":{"date-parts":[[2021,11,17]]},"DOI":"10.1080\/01691864.2021.1977696","type":"journal-article","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T20:05:51Z","timestamp":1632945951000},"page":"1359-1373","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":5,"title":["SegVisRL: development of a robot's neural visuomotor and planning system for lunar exploration"],"prefix":"10.1080","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-6480","authenticated-orcid":false,"given":"Tamir","family":"Blum","sequence":"first","affiliation":[{"name":"Department of Aerospace Engineering, Tohoku University, Sendai, Japan"}]},{"given":"Gabin","family":"Paillet","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Tohoku University, Sendai, Japan"}]},{"given":"Watcharawut","family":"Masawat","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Tohoku University, Sendai, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3889-5877","authenticated-orcid":false,"given":"Kazuya","family":"Yoshida","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Tohoku University, Sendai, Japan"}]}],"member":"301","published-online":{"date-parts":[[2021,9,29]]},"reference":[{"key":"CIT0001","doi-asserted-by":"publisher","DOI":"10.1109\/AERO47225.2020.9172271"},{"key":"CIT0002","unstructured":"Sutton RS, Barto AG. Reinforcement learning: an introduction. 2018. p. 352."},{"key":"CIT0003","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/294"},{"key":"CIT0004","unstructured":"Zhang J, Tai L, Liu M, et\u00a0al. Neural SLAM: learning to explore with external memory. 2020 Dec. ArXiv:1706.09520 [cs]."},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"CIT0006","unstructured":"Mnih V, Badia AP, Mirza M, et\u00a0al. Asynchronous methods for deep reinforcement learning. 2016 Jun. ArXiv:1602.01783 [cs]."},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"CIT0008","unstructured":"Mirowski P, Pascanu R, Viola F, et\u00a0al. Learning to navigate in complex environments. 2017 Jan. ArXiv:1611.03673 [cs]."},{"key":"CIT0009","unstructured":"Mnih V, Kavukcuoglu K, Silver D, et\u00a0al. Playing Atari with deep reinforcement learning. 2013. p. 9."},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"CIT0011","unstructured":"Surmann H, Jestel C, Marchel R, et\u00a0al. Deep reinforcement learning for real autonomous mobile robot navigation in indoor environments. 2020 May. arXiv: 2005.13857 [cs]. Available from: http:\/\/arxiv.org\/abs\/2005.13857."},{"key":"CIT0012","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"CIT0013","unstructured":"Stefanuk B, Pascual A, Skonieczny K, et\u00a0al. Detecting novelties on planetary surfaces with autoencoders. 2020. p. 8."},{"key":"CIT0014","unstructured":"Raimalwala K, Faragalli M, Smal E, et\u00a0al. Enabling autonomy in commercial-class lunar missions. 2020. p. 8."},{"key":"CIT0015","doi-asserted-by":"publisher","DOI":"10.1016\/j.jterra.2020.12.003"},{"key":"CIT0016","unstructured":"Banerjee S, Harrison J, Furlong PM, et\u00a0al. i-SAIRAS2020-PapAerDs A(20P20T) ive meta-learning for identification of rover-terrain dynamics. 2020. p. 8."},{"key":"CIT0017","unstructured":"Inotsume H, Kubota T. Slip prediction for exploration rover based on transfer learning. 2020. p. 6."},{"key":"CIT0018","unstructured":"Bonardi S, Nikaido T, Kubota T. Novel robotic exoskeletons for space exploration and colonization. 2020. p. 3."},{"key":"CIT0019","unstructured":"Sakamoto K, Ijspeert AJ, Kubota T. Evaluation of hopping robot locomotion for planetary exploration in a 3D simulator. 2020. p. 5."},{"key":"CIT0020","unstructured":"Chien S, Boerkoel J, Mason J, et\u00a0al. Space ground sensorwebs for volcano monitoring. 2020. p. 5."},{"key":"CIT0021","unstructured":"Burtz LJ, Dubois F, Guy N. Human-robot teaming strategy for fast teleoperation of a lunar resource exploration rover. 2020 Oct."},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.053"},{"key":"CIT0024","unstructured":"Zhu H, Yu J, Gupta A, et\u00a0al. The ingredients of real-world robotic reinforcement learning. 2020 Apr. ArXiv: 2004.12570 [cs, stat]."},{"key":"CIT0025","unstructured":"Mahmood AR, Korenkevych D, Komer BJ, et\u00a0al. Setting up a reinforcement learning task with a real-world robot. 2018 Mar. ArXiv: 1803.07067 [cs, stat]."},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC48513.2020.9065237"},{"key":"CIT0027","doi-asserted-by":"publisher","DOI":"10.1109\/SII46433.2020.9025928"},{"key":"CIT0028","unstructured":"Blum T, Paillet G, Laine M, et\u00a0al. RL STaR platform: reinforcement learning for simulation based training of robots. 2020 Sep. ArXiv: 2009.09595 [cs]."},{"key":"CIT0029","unstructured":"Blum T, Yoshida K. PPMC RL training algorithm: rough terrain intelligent robots through reinforcement learning. 2020 Mar. ArXiv: 2003.02655 [cs, eess, stat]."},{"key":"CIT0030","unstructured":"Surovik D, Wang K, Bekris KE. Adaptive tensegrity locomotion on rough terrain via reinforcement learning. 2018 Sep. ArXiv: 1809.10710 [cs]."},{"key":"CIT0031","unstructured":"Kim D, Lee J, Sentis L. Robust dynamic locomotion via reinforcement learning and novel whole body controller. 2017 Aug."},{"key":"CIT0032","unstructured":"Peng XB, Coumans E, Zhang T, et\u00a0al. Learning agile robotic locomotion skills by imitating animals. 2020. p. 14."},{"key":"CIT0033","unstructured":"Sharifzadeh S, Chiotellis I, Triebel R, et\u00a0al. Learning to drive using inverse reinforcement learning and deep Q-networks. 2017 Sep. ArXiv: 1612.03653 [cs]."},{"key":"CIT0034","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073987"},{"key":"CIT0035","unstructured":"Rusu AA, Vecerik M, Roth\u00f6rl T, et\u00a0al. Sim-to-real robot learning from pixels with progressive nets. 2018 May. ArXiv: 1610.04286 [cs]."},{"key":"CIT0036","unstructured":"Levine S, Finn C, Darrell T, et\u00a0al. End-to-end training of deep visuomotor policies. 2015. p. 40."},{"key":"CIT0037","unstructured":"Blum T, Paillet G, Masawat W, et\u00a0al. SegVisRL: visuomotor development for a lunar rover for hazard avoidance using camera images. 2021 Mar. ArXiv: 2103.14422. [cs, eess]. Available from: http:\/\/arxiv.org\/abs\/2103.14422."},{"key":"CIT0038","unstructured":"Espeholt L, Soyer H, Munos R, et\u00a0al. IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. 2018 Jun. ArXiv: 1802.01561 [cs]."},{"key":"CIT0039","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"CIT0040","unstructured":"Coumans E. bulletphysics\/bullet3. 2013. Available from: https:\/\/github.com\/bulletphysics\/bullet3."},{"key":"CIT0041","unstructured":"Wu Y, Mansimov E, Liao S, et\u00a0al. Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. 2017 Aug. ArXiv: 1708.05144 [cs]."},{"key":"CIT0042","unstructured":"Schulman J, Wolski F, Dhariwal P, et\u00a0al. Proximal policy optimization algorithms. 2017 Aug. ArXiv: 1707.06347 [cs]."},{"key":"CIT0043","unstructured":"Martens J, Grosse R. Optimizing neural networks with Kronecker-factored approximate curvature. 2020 Jun. ArXiv: 1503.05671 [cs, stat]."},{"key":"CIT0044","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559732"},{"key":"CIT0045","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700903"},{"key":"CIT0046","first-page":"1","author":"Endo M","year":"2021","journal-title":"Robotica"}],"container-title":["Advanced Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01691864.2021.1977696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T18:58:24Z","timestamp":1637953104000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/01691864.2021.1977696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,29]]},"references-count":46,"journal-issue":{"issue":"21-22","published-print":{"date-parts":[[2021,11,17]]}},"alternative-id":["10.1080\/01691864.2021.1977696"],"URL":"https:\/\/doi.org\/10.1080\/01691864.2021.1977696","relation":{},"ISSN":["0169-1864","1568-5535"],"issn-type":[{"value":"0169-1864","type":"print"},{"value":"1568-5535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,29]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tadr20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2021-02-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-04","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}