{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T12:49:20Z","timestamp":1768999760866,"version":"3.49.0"},"reference-count":71,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"103","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":365,"URL":"https:\/\/www.science.org\/content\/page\/science-licenses-journal-article-reuse"}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2025,6,18]]},"abstract":"<jats:p>Neuromorphic computing offers a transformative pathway to overcome the computational and energy challenges faced in deploying robotic localization and navigation systems at the edge. Visual place recognition, a critical component for navigation, is often hampered by the high resource demands of conventional systems, making them unsuitable for small-scale robotic platforms, which still require accurate long-endurance localization. Although neuromorphic approaches offer potential for greater efficiency, real-time edge deployment remains constrained by the complexity of biorealistic networks. To overcome this challenge, fusion of hardware and algorithms is critical when using this specialized computing paradigm. Here, we demonstrate a neuromorphic localization system that performs competitive place recognition in up to 8 kilometers of traversal using models as small as 180 kilobytes with 44,000 parameters while consuming less than 8% of the energy required by conventional methods. Our system, locational encoding with neuromorphic systems (LENS), integrates spiking neural networks, an event-based dynamic vision sensor, and a neuromorphic processor within a single SynSense Speck chip, enabling real-time, energy-efficient localization on a hexapod robot. When compared with a benchmark place recognition method, sum of absolute differences, LENS performs comparably in overall precision. LENS represents an accurate fully neuromorphic localization system capable of large-scale, on-device deployment for energy-efficient robotic place recognition. Neuromorphic computing enables resource-constrained robots to perform energy-efficient, accurate localization.<\/jats:p>","DOI":"10.1126\/scirobotics.ads3968","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:00:56Z","timestamp":1750269656000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":2,"title":["A compact neuromorphic system for ultra\u2013energy-efficient, on-device robot localization"],"prefix":"10.1126","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0259-3642","authenticated-orcid":true,"given":"Adam D.","family":"Hines","sequence":"first","affiliation":[{"name":"QUT Centre for Robotics, Queensland University of Technology, 2 George St, Brisbane, QLD 4001, Australia."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5162-1793","authenticated-orcid":true,"given":"Michael","family":"Milford","sequence":"additional","affiliation":[{"name":"QUT Centre for Robotics, Queensland University of Technology, 2 George St, Brisbane, QLD 4001, Australia."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2183-017X","authenticated-orcid":true,"given":"Tobias","family":"Fischer","sequence":"additional","affiliation":[{"name":"QUT Centre for Robotics, Queensland University of Technology, 2 George St, Brisbane, QLD 4001, Australia."}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3310859"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107760"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3054937"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"G. Berton C. Masone B. Caputo \u201cRethinking visual geo-localization for large-scale applications \u201d in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2022) pp. 4878\u20134888.","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"G. Neuhold T. Ollmann S. R. Bul\u00f2 P. Kontschieder \u201cThe Mapillary Vistas dataset for semantic understanding of street scenes \u201d in IEEE International Conference on Computer Vision (IEEE 2017) pp. 5000\u20135009.","DOI":"10.1109\/ICCV.2017.534"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"M. Cordts M Omran S. Ramos T. Rehfeld M. Enzweiler R. Benenson U. Franke S. Roth B. Schiele \u201cThe Cityscapes dataset for semantic urban scene understanding \u201d in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2016) pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"S. Izquierdo J. Civera \u201cOptimal transport aggregation for visual place recognition \u201d in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2024) pp. 17658\u201317668.","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"G. Orchard E. Paxon Frady Daniel Ben Dayan Rubin S. Sanborn S. B. Shrestha F. T. Sommer M. Davies \u201cEfficient neuromorphic signal processing with Loihi 2 \u201d in IEEE Workshop on Signal Processing Systems (IEEE 2021) pp. 254\u2013259.","DOI":"10.1109\/SiPS52927.2021.00053"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"E. Painkras L. A. Plana J. Garside S. Temple S. Davidson J. Pepper D. Clark C. Patterson S. Furber \u201cSpiNNaker: A multi-core system-on-chip for massively-parallel neural net simulation \u201d in IEEE Custom Integrated Circuits Conference (IEEE 2012) pp. 1\u20134.","DOI":"10.1109\/CICC.2012.6330636"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg3679"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adk0310"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6996"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pneurobio.2024.102569"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.03.007"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi8237"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2004520"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-019-00806-9"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8040350"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"L. Wang S. X. Yang M. Biglarbegian \u201cBio-inspired navigation of mobile robots \u201d in International Conference on Autonomous and Intelligent Systems (Springer 2012) pp. 59\u201368.","DOI":"10.1007\/978-3-642-31368-4_8"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"T. Joseph T. Fischer M. Milford \u201cTrajectory tracking via multiscale continuous attractor networks \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2023) pp. 368\u2013375.","DOI":"10.1109\/IROS55552.2023.10341938"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3308088"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"S. Hussaini M. Milford T. Fischer \u201cEnsembles of compact region-specific and regularized spiking neural networks for scalable place recognition \u201d in IEEE International Conference on Robotics and Automation (IEEE 2023) pp. 4200\u20134207.","DOI":"10.1109\/ICRA48891.2023.10160749"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3149030"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3508053"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"A. D. Hines P. G. Stratton M. Milford T. Fischer \u201cVPRTempo: A fast temporally encoded spiking neural network for visual place recognition \u201d in IEEE International Conference on Robotics and Automation (IEEE 2024) pp. 10200\u201310207.","DOI":"10.1109\/ICRA57147.2024.10610918"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-023-00150-1"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104362"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","unstructured":"G. Tang A. Shah K. P. Michmizos \u201cSpiking neural network on neuromorphic hardware for energy-efficient unidimensional SLAM \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2019) pp. 4176\u20134181.","DOI":"10.1109\/IROS40897.2019.8967864"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"F. Galluppi J. Conradt T. Stewart C. Eliasmith T. Horiuchi J. Tapson B. Tripp S. Furber R. Etienne-Cummings \u201cLive demo: Spiking ratSLAM: Rat hippocampus cells in spiking neural hardware \u201d in IEEE Biomedical Circuits and Systems Conference (IEEE 2012) pp. 91\u201391.","DOI":"10.1109\/BioCAS.2012.6418493"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.18-24-10464.1998"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967324"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28487-2"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3008413"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.3390\/chips2010002"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106838"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2015.2474396"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1424-8"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"B. J. Shastri A. N. Tait Thomas Ferreira de Lima M. A. Nahmias H.-T. Peng P. R. Prucnal \u201cPrinciples of neuromorphic photonics \u201d in Encyclopedia of Complexity and Systems Science (Springer 2018) pp. 83\u2013118.","DOI":"10.1007\/978-1-4939-6883-1_702"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi0591"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1234962"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.590163"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-47811-6"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3025505"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"M. J. Milford G. F. Wyeth \u201cSeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights \u201d in IEEE International Conference on Robotics and Automation (IEEE 2012) pp. 1643\u20131649.","DOI":"10.1109\/ICRA.2012.6224623"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216226"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","unstructured":"A. J. Lee A. Kim \u201cEventVLAD: Visual place recognition with reconstructed edges from event cameras \u201d in 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE 2021) pp. 2247\u20132252.","DOI":"10.1109\/IROS51168.2021.9635907"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3298828"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2007.914337"},{"key":"e_1_3_2_52_2","doi-asserted-by":"crossref","unstructured":"S. Bian L. Schulthess G. Rutishauser A. D. Mauro L. Benini M. Magno \u201cColibriUAV: An ultra-fast energy-efficient neuromorphic edge processing UAV-platform with event-based and frame-based cameras \u201d in IEEE International Workshop on Advances in Sensors and Interfaces (IEEE 2023) pp. 287\u2013292.","DOI":"10.1109\/IWASI58316.2023.10164354"},{"key":"e_1_3_2_53_2","first-page":"152","article-title":"Energy efficiency of underwater robots","volume":"48","author":"Kelasidi E.","year":"2015","unstructured":"E. Kelasidi, K. Y. Pettersen, J. T. Gravdahl, Energy efficiency of underwater robots. IFAC Conference on Manoeuvring and Control of Marine Craft 48, 152\u2013159 (2015).","journal-title":"IFAC Conference on Manoeuvring and Control of Marine Craft"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00129"},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"R. Islam H. Habibullah \u201cA semantically aware place recognition system for loop closure of a visual SLAM system \u201d in 2021 4th International Conference on Mechatronics Robotics and Automation (ICMRA) (IEEE 2021) pp. 117\u2013121.","DOI":"10.1109\/ICMRA53481.2021.9675715"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3185766"},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"G. B. Nair M. Milford T. Fischer \u201cEnhancing visual place recognition via fast and slow adaptive biasing in event cameras \u201d in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IEEE 2024) pp. 3356\u20133363.","DOI":"10.1109\/IROS58592.2024.10802384"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27653-2"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42470-5"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1018006"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1161592"},{"key":"e_1_3_2_63_2","unstructured":"T. Chen S. Kornblith M. Norouzi G. Hinton \u201cA simple framework for contrastive learning of visual representations \u201d in International Conference on Machine Learning (PMLR 2020) pp. 1597\u20131607."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau0307"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.05.033"},{"key":"e_1_3_2_66_2","doi-asserted-by":"crossref","unstructured":"M. Milford G. Wyeth D. Prasser \u201cRatSLAM: A hippocampal model for simultaneous localization and mapping \u201d in IEEE International Conference on Robotics and Automation (IEEE 2004) pp. 403\u2013408.","DOI":"10.1109\/ROBOT.2004.1307183"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1190515"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.02.023"},{"key":"e_1_3_2_69_2","doi-asserted-by":"crossref","unstructured":"L. Liu J. Chen M. Brocanelli W. Shi \u201cE2M: An energy-efficient middleware for computer vision applications on autonomous mobile robots \u201d in ACM\/IEEE Symposium on Edge Computing (IEEE 2019) pp. 59\u201373.","DOI":"10.1145\/3318216.3363302"},{"key":"e_1_3_2_70_2","unstructured":"P. G. Stratton A. Wabnitz C. Essam A. Cheung T. J. Hamilton Making a Spiking Net Work: Robust brain-like unsupervised machine learning. arXiv:2208.01204 [cs.NE] (2022)."},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.638474"},{"key":"e_1_3_2_72_2","unstructured":"S. Garg M. Vankadari M. Milford \u201cSeqMatchNet: Contrastive learning with sequence matching for place recognition and relocalization \u201d in Proceedings of the 5th Conference on Robot Learning (PMLR 2022) pp. 429\u2013443."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.ads3968","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.ads3968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:01:21Z","timestamp":1750269681000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.ads3968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":71,"journal-issue":{"issue":"103","published-print":{"date-parts":[[2025,6,18]]}},"alternative-id":["10.1126\/scirobotics.ads3968"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.ads3968","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"assertion":[{"value":"2024-08-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eads3968"}}