{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:07:49Z","timestamp":1780913269343,"version":"3.54.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73202-7_5","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:16:37Z","timestamp":1732112197000},"page":"76-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Reinforcement Learning Meets Visual Odometry"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-1176","authenticated-orcid":false,"given":"Nico","family":"Messikommer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3964-8552","authenticated-orcid":false,"given":"Giovanni","family":"Cioffi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2223-4265","authenticated-orcid":false,"given":"Mathias","family":"Gehrig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3831-6778","authenticated-orcid":false,"given":"Davide","family":"Scaramuzza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Burri, M., et al.: The EuRoC micro aerial vehicle datasets. The International Journal of Robotics Research (2016). https:\/\/doi.org\/10.1177\/0278364915620033","DOI":"10.1177\/0278364915620033"},{"issue":"6","key":"5_CR2","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1109\/TRO.2016.2624754","volume":"32","author":"C Cadena","year":"2016","unstructured":"Cadena, C., et al.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans. Rob. 32(6), 1309\u20131332 (2016)","journal-title":"IEEE Trans. Rob."},{"issue":"6","key":"5_CR3","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Gomez, J.J., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial and multi-map SLAM. IEEE Trans. Rob. 37(6), 1874\u20131890 (2021)","journal-title":"IEEE Trans. Rob."},{"issue":"5","key":"5_CR4","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1109\/TPAMI.2019.2956703","volume":"43","author":"X Dong","year":"2019","unstructured":"Dong, X., Shen, J., Wang, W., Shao, L., Ling, H., Porikli, F.: Dynamical hyperparameter optimization via deep reinforcement learning in tracking. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1515\u20131529 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"5_CR5","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2018","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 611\u2013625 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2658577","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"5_CR6","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/TRO.2016.2623335","volume":"33","author":"C Forster","year":"2017","unstructured":"Forster, C., Zhang, Z., Gassner, M., Werlberger, M., Scaramuzza, D.: SVO: semidirect visual odometry for monocular and multicamera systems. IEEE Trans. Robot. 33(2), 249\u2013265 (2017). https:\/\/doi.org\/10.1109\/TRO.2016.2623335","journal-title":"IEEE Trans. Robot."},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"5_CR8","unstructured":"Jaegle, A., et al.: Perceiver IO: a general architecture for structured inputs & outputs. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"5_CR9","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver: general perception with iterative attention. In: Proceedings of the International Conference on Machine Learning (ICML) (2021)"},{"key":"5_CR10","unstructured":"Jomaa, H.S., Grabocka, J., Schmidt-Thieme, L.: Hyp-RL: hyperparameter optimization by reinforcement learning. arXiv preprint arXiv:1906.11527 (2019)"},{"issue":"5","key":"5_CR11","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"5_CR12","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: Reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021). http:\/\/jmlr.org\/papers\/v22\/20-1364.html"},{"issue":"4","key":"5_CR13","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/MRA.2011.943233","volume":"18","author":"D Scaramuzza","year":"2011","unstructured":"Scaramuzza, D., Fraundorfer, F.: Visual odometry [tutorial]. IEEE Robot. Autom. Mag. 18(4), 80\u201392 (2011)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"5_CR14","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Sheng, L., Xu, D., Ouyang, W., Wang, X.: Unsupervised collaborative learning of keyframe detection and visual odometry towards monocular deep SLAM. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4302\u20134311 (2019)","DOI":"10.1109\/ICCV.2019.00440"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of rgb-d slam systems. In: Proceedings of the International Conference on Intelligent Robot Systems (IROS) (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part II. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"5_CR18","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed, Z., Deng, J.: Droid-SLAM: deep visual slam for monocular, stereo, and RGB-D cameras. Adv. Neural. Inf. Process. Syst. 34, 16558\u201316569 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR19","unstructured":"Teed, Z., Lipson, L., Deng, J.: Deep patch visual odometry. arXiv preprint arXiv:2208.04726 (2022)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13(4) (1991)","DOI":"10.1109\/34.88573"},{"key":"5_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"issue":"7","key":"5_CR22","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.imavis.2011.01.006","volume":"29","author":"G Vogiatzis","year":"2011","unstructured":"Vogiatzis, G., Hern\u00e1ndez, C.: Video-based, real-time multi-view stereo. Image Vis. Comput. 29(7), 434\u2013441 (2011)","journal-title":"Image Vis. Comput."},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 2043\u20132050. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"5_CR24","unstructured":"Wang, W., Hu, Y., Scherer, S.: TartanVO: a generalizable learning-based vo. In: Conference on Robot Learning, pp. 1761\u20131772. PMLR (2021)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: TartanAir: a dataset to push the limits of visual SLAM. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Ye, W., et al.: PVO: panoptic visual odometry. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589 (2023)","DOI":"10.1109\/CVPR52729.2023.00924"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Scaramuzza, D.: A tutorial on quantitative trajectory evaluation for visual (-inertial) odometry. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7244\u20137251. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593941"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:06:19Z","timestamp":1732115179000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}