{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T03:46:15Z","timestamp":1784000775514,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss Federal Institute of Technology Zurich"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In this paper, we propose a novel loop closure detection algorithm that uses graph attention neural networks to encode semantic graphs to perform place recognition and then use semantic registration to estimate the 6 DoF relative pose constraint. Our place recognition algorithm has two key modules, namely, a semantic graph encoder module and a graph comparison module. The semantic graph encoder employs graph attention networks to efficiently encode spatial, semantic and geometric information from the semantic graph of the input point cloud. We then use self-attention mechanism in both node-embedding and graph-embedding steps to create distinctive graph vectors. The graph vectors of the current scan and a keyframe scan are then compared in the graph comparison module to identify a possible loop closure. Specifically, employing the difference of the two graph vectors showed a significant improvement in performance, as shown in ablation studies. Lastly, we implemented a semantic registration algorithm that takes in loop closure candidate scans and estimates the relative 6 DoF pose constraint for the LiDAR SLAM system. Extensive evaluation on public datasets shows that our model is more accurate and robust, achieving 13% improvement in maximum F1 score on the SemanticKITTI dataset, when compared to the baseline semantic graph algorithm. For the benefit of the community, we open-source the complete implementation of our proposed algorithm and custom implementation of semantic registration at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/crepuscularlight\/SemanticLoopClosure\" ext-link-type=\"uri\">https:\/\/github.com\/crepuscularlight\/SemanticLoopClosure<\/jats:ext-link>.<\/jats:p>","DOI":"10.1007\/s10846-025-02223-6","type":"journal-article","created":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T08:29:03Z","timestamp":1736584143000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8912-2834","authenticated-orcid":false,"given":"Liudi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruben","family":"Mascaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignacio","family":"Alzugaray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai Manoj","family":"Prakhya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Karrer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Margarita","family":"Chli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"key":"2223_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii A, et\u00a0al.: NetVLAD: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5297\u20135307. (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"2223_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Y., Ding, H., Bian, S., et\u00a0al.: SimGNN: A Neural Network Approach to Fast Graph Similarity Computation. In: Proceedings of the twelfth ACM international conference on web search and data mining. Association for computing machinery, New York, NY, USA, WSDM \u201919, pp. 384\u2013392. (2019) doi10.1145\/3289600.3290967","DOI":"10.1145\/3289600.3290967"},{"key":"2223_CR3","doi-asserted-by":"crossref","unstructured":"Behley, J., Garbade, M., Milioto, A., et\u00a0al.:SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences. In: Proc. of the IEEE\/CVF International Conf.\u00a0on Computer Vision (ICCV). (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"2223_CR4","doi-asserted-by":"crossref","unstructured":"Bosse, M., Zlot, R.: Place recognition using keypoint voting in large 3d lidar datasets. In: 2013 IEEE international conference on robotics and automation. pp. 2677\u20132684. (2013). doi10.1109\/ICRA.2013.6630945","DOI":"10.1109\/ICRA.2013.6630945"},{"key":"2223_CR5","unstructured":"Brody, S., Alon, U., Yahav, E.: How attentive are graph attention networks? In: International conference on learning representations. (2022). https:\/\/openreview.net\/forum?id=F72ximsx7C1"},{"key":"2223_CR6","unstructured":"Bruna, J., Zaremba, W., Szlam, A., et\u00a0al.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (ICLR2014), CBLS, April 2014. (2014)"},{"issue":"4","key":"2223_CR7","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1109\/TRO.2022.3150683","volume":"38","author":"D Cattaneo","year":"2022","unstructured":"Cattaneo, D., Vaghi, M., Valada, A.: LCDNet: deep loop closure detection and point cloud registration for LiDAR SLAM. IEEE Trans. Rob. 38(4), 2074\u20132093 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"2223_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Milioto, A., Palazzolo, E., et\u00a0al.: SuMa++: Efficient LiDAR-based Semantic SLAM. In: Proceedings of the IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems (IROS). (2019)","DOI":"10.1109\/IROS40897.2019.8967704"},{"key":"2223_CR9","doi-asserted-by":"crossref","unstructured":"Dub\u00e9, R., Dugas, D., Stumm, E., et\u00a0al.: SegMatch: segment based place recognition in 3d point clouds. In: IEEE International Conference on Robotics and Automation (ICRA). (2017)","DOI":"10.1109\/ICRA.2017.7989618"},{"key":"2223_CR10","doi-asserted-by":"publisher","unstructured":"Dub\u00e9, R., Cramariuc, A., Dugas, D., et\u00a0al.: SegMap: 3D segment mapping using data-driven descriptors. In: Robotics: science and systems XIV. robotics: science and systems foundation. (2018). https:\/\/doi.org\/10.15607\/rss.2018.xiv.003","DOI":"10.15607\/rss.2018.xiv.003"},{"key":"2223_CR11","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":"2223_CR12","doi-asserted-by":"publisher","unstructured":"He, L., Wang, X., Zhang, H.: M2DP: A novel 3D point cloud descriptor and its application in loop closure detection. In: 2016 IEEE\/RSJ international conference on Intelligent Robots and Systems (IROS). pp.231\u2013237. (2016). https:\/\/doi.org\/10.1109\/IROS.2016.7759060","DOI":"10.1109\/IROS.2016.7759060"},{"key":"2223_CR13","unstructured":"Hong, Y., Zhen, H., Chen, P., et\u00a0al.: 3D-LLM: Injecting the 3D world into large language models. arXiv. (2023)"},{"key":"2223_CR14","doi-asserted-by":"publisher","unstructured":"Kim, G., Kim, A.: Scan context: egocentric spatial descriptor for place recognition within 3D point cloud map. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp 4802\u20134809. (2018). https:\/\/doi.org\/10.1109\/IROS.2018.8593953","DOI":"10.1109\/IROS.2018.8593953"},{"issue":"3","key":"2223_CR15","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TRO.2021.3116424","volume":"38","author":"G Kim","year":"2021","unstructured":"Kim, G., Choi, S., Kim, A.: Scan Context++: structural place recognition robust to rotation and lateral variations in urban environments. IEEE Trans. Rob. 38(3), 1856\u20131874 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"2223_CR16","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International conference on learning representations. (2017). https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"2223_CR17","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., et\u00a0al.: Segment anything. (2023). arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2223_CR18","doi-asserted-by":"publisher","unstructured":"Komorowski, J.: MinkLoc3D: point cloud based large-scale place recognition. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1789\u20131798. (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00183","DOI":"10.1109\/WACV48630.2021.00183"},{"key":"2223_CR19","doi-asserted-by":"publisher","unstructured":"Kong, X., Yang, X., Zhai, G., et\u00a0al.: Semantic Graph Based Place Recognition for 3D Point Clouds. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp 8216\u20138223. (2020) https:\/\/doi.org\/10.1109\/IROS45743.2020.9341060","DOI":"10.1109\/IROS45743.2020.9341060"},{"key":"2223_CR20","doi-asserted-by":"publisher","unstructured":"Li, G., M\u00fcller, M., Qian, G., et al.: DeepGCNs: making GCNs go as deep as CNNs 45. 6, 6923\u20136939 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2021.3074057","DOI":"10.1109\/TPAMI.2021.3074057"},{"key":"2223_CR21","doi-asserted-by":"publisher","unstructured":"Li, L., Kong, X., Zhao, X., et\u00a0al.: SSC: Semantic Scan Context for Large-Scale Place Recognition. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE Press, pp. 2092\u20132099. (2021). https:\/\/doi.org\/10.1109\/IROS51168.2021.9635904","DOI":"10.1109\/IROS51168.2021.9635904"},{"key":"2223_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Kong, X., Zhao, X., et\u00a0al.: SA-LOAM: Semantic-aided LiDAR SLAM with Loop Closure. In: 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp 7627\u20137634. (2021)","DOI":"10.1109\/ICRA48506.2021.9560884"},{"key":"2223_CR23","unstructured":"Liao, Y., Xie, J., Geiger, A.: Kitti-360: A novel dataset and benchmarks for urban scene understanding in 2d and 3d. (2021). arXiv:2109.13410"},{"key":"2223_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, S., Suo, C., et\u00a0al.: LPD-Net: 3D point cloud learning for large-scale place recognition and environment analysis. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 2831\u20132840. (2019)","DOI":"10.1109\/ICCV.2019.00292"},{"key":"2223_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International conference on learning representations. (2019). https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"issue":"3","key":"2223_CR26","doi-asserted-by":"publisher","first-page":"6958","DOI":"10.1109\/LRA.2022.3178797","volume":"7","author":"J Ma","year":"2022","unstructured":"Ma, J., Zhang, J., Xu, J., et al.: Overlaptransformer: an efficient and yaw-angle-invariant transformer network for lidar-based place recognition. IEEE Robot Autom Lett 7(3), 6958\u20136965 (2022). https:\/\/doi.org\/10.1109\/LRA.2022.3178797","journal-title":"IEEE Robot Autom Lett"},{"key":"2223_CR27","doi-asserted-by":"crossref","unstructured":"Magnusson, M., Andreasson, H., Nuchter, A., et\u00a0al.: Appearance-based Loop Detection from 3D laser data using the normal distributions transform. In: 2009 IEEE international conference on robotics and automation. pp 23\u201328, (2009). doi10.1109\/ROBOT.2009.5152712","DOI":"10.1109\/ROBOT.2009.5152712"},{"issue":"3","key":"2223_CR28","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1109\/LRA.2017.2667721","volume":"2","author":"SM Prakhya","year":"2017","unstructured":"Prakhya, S.M., Lin, J., Chandrasekhar, V., et al.: 3DHoPD: a fast low-dimensional 3-D descriptor. IEEE Robot Autom Lett 2(3), 1472\u20131479 (2017). https:\/\/doi.org\/10.1109\/LRA.2017.2667721","journal-title":"IEEE Robot Autom Lett"},{"key":"2223_CR29","doi-asserted-by":"publisher","unstructured":"Prokhorov, D., Zhukov, D., Barinova, O., et\u00a0al.: Measuring robustness of visual SLAM. In: 2019 16th international conference on Machine Vision Applications (MVA). pp. 1\u20136. (2019). https:\/\/doi.org\/10.23919\/MVA.2019.8758020","DOI":"10.23919\/MVA.2019.8758020"},{"key":"2223_CR30","unstructured":"Qi, C.R., Su, H., Mo, K., et\u00a0al.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 652\u2013660. (2017)"},{"key":"2223_CR31","unstructured":"Quigley, M., Conley, K., Gerkey, B., et\u00a0al.: ROS: an open-source robot operating system. In: ICRA workshop on open source software. (2009)"},{"key":"2223_CR32","unstructured":"Radford, A., Kim, J.W., Hallacy, C, et\u00a0al (2021) Learning Transferable Visual Models from Natural Language Supervision. In: International conference on machine learning, PMLR, pp 8748\u20138763"},{"key":"2223_CR33","doi-asserted-by":"publisher","unstructured":"Rusu RB, Blodow N, Beetz M (2009) Fast Point Feature Histograms (FPFH) for 3D Registration. In: 2009 IEEE International Conference on Robotics and Automation, pp 3212\u20133217, https:\/\/doi.org\/10.1109\/ROBOT.2009.5152473","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"2223_CR34","doi-asserted-by":"publisher","unstructured":"Salti, S., Tombari, F., Di Stefano, L.: SHOT: Unique Signatures of Histograms for Surface and Texture Description. Comput. Vis. Image Underst. 125, 251\u201326 (2014). https:\/\/doi.org\/10.1016\/j.cviu.2014.04.011, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314214000988","DOI":"10.1016\/j.cviu.2014.04.011"},{"key":"2223_CR35","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Lee, G.H.: PointNetVLAD: deep point cloud based retrieval for large-scale place recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (2018)","DOI":"10.1109\/CVPR.2018.00470"},{"key":"2223_CR36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., et\u00a0al. (eds) Advances in neural information processing systems, vol\u00a030. Curran Associates, Inc., (2017) https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"2223_CR37","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., et\u00a0al.: Graph attention networks. In: International conference on learning representations. (2018). https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"2223_CR38","doi-asserted-by":"publisher","unstructured":"Wang, H., Wang, C., Xie, L.: Intensity scan context: coding intensity and geometry relations for loop closure detection. In: 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, (2020). https:\/\/doi.org\/10.1109\/icra40945.2020.9196764","DOI":"10.1109\/icra40945.2020.9196764"},{"key":"2223_CR39","doi-asserted-by":"publisher","unstructured":"Wang, H., Wang, C., Chen, C.L., et\u00a0al.: F-LOAM : Fast LiDAR odometry and mapping. In: 2021 IEEE\/RSJ international conference on Intelligent Robots and Systems (IROS). IEEE, (2021). https:\/\/doi.org\/10.1109\/iros51168.2021.9636655","DOI":"10.1109\/iros51168.2021.9636655"},{"issue":"5","key":"2223_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., et al.: Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics (tog) 38(5), 1\u201312 (2019)","journal-title":"ACM Transactions on Graphics (tog)"},{"key":"2223_CR41","doi-asserted-by":"publisher","unstructured":"Wu, Z., Song, S., Khosla, A., et\u00a0al.: 3D ShapeNets: a deep representation for volumetric shapes. In: 2015 IEEE conference on Computer Vision and Pattern Recognition (CVPR). pp. 1912\u20131920. (2015) . https:\/\/doi.org\/10.1109\/CVPR.2015.7298801","DOI":"10.1109\/CVPR.2015.7298801"}],"container-title":["Journal of Intelligent &amp; Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-025-02223-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-025-02223-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-025-02223-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T13:02:26Z","timestamp":1743858146000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-025-02223-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["2223"],"URL":"https:\/\/doi.org\/10.1007\/s10846-025-02223-6","relation":{},"ISSN":["1573-0409"],"issn-type":[{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,11]]},"assertion":[{"value":"19 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest or competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest\/Competing Interests"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Consent for publication was obtained from all participants whose data is included in this manuscript.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"13"}}