{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:26:48Z","timestamp":1792783608361,"version":"4.5.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100021130","name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","doi-asserted-by":"publisher","award":["19A21026E"],"award-info":[{"award-number":["19A21026E"]}],"id":[{"id":"10.13039\/100021130","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz, Germany","award":["19A21026E"],"award-info":[{"award-number":["19A21026E"]}],"id":[{"id":"https:\/\/ror.org\/02vgg2808","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    AI-based environment perception systems are a key enabler of autonomous driving, yet assuring their safety remains a fundamental challenge. Just like human drivers, such perception systems will never be completely safe to use, in the same way as human driving will never be completely safe. Due to the inherent limitations of machine-learned models operating in open and only partially foreseeable environments, complete correctness cannot be guaranteed, making it necessary to argue the absence of\n                    <jats:italic>unreasonable risk<\/jats:italic>\n                    rather than absolute safety. To help with such a proof, the concept of\n                    <jats:italic>Safety of the Intended Functionality<\/jats:italic>\n                    was introduced with ISO norm 21448 (SOTIF), which concerns making a structured safety argument of the correct functioning of a system component of an autonomous vehicle in the operational domain it was designed for. The SOTIF norm defines a set of activities for this purpose, but leaves considerable freedom regarding how such a proof is made. In this paper, we present a conceptual and process-oriented framework that integrates an ensemble of runtime monitors into a SOTIF-oriented development process for AI-based environment perception systems.The proposed monitoring ensemble consists of complementary monitor types that address different sources of uncertainty in perception systems, including inconsistencies between redundant systems, deviations from known input\u2013output behavior, and unfamiliar internal activation patterns. We analyze how these monitors may support selected SOTIF activities, including risk identification, verification and validation, and operational-phase feedback.Rather than providing an implementation or quantitative evaluation, this work focuses on the systematic integration of monitoring into the SOTIF lifecycle and its role in structuring safety arguments. The monitoring ensemble is intended to facilitate the identification of potential near-failure situations, support scenario discovery, and provide additional evidence that may be used when assessing residual risk. As such, it contributes to concretizing the activities in a SOTIF-based development process for AI-based perception systems.\n                  <\/jats:p>","DOI":"10.1007\/s44163-026-02186-z","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:47:03Z","timestamp":1789717623000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Addressing SOTIF with a runtime monitor ensemble for AI-based perception systems"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3218-3214","authenticated-orcid":false,"given":"Felix","family":"Schaller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R\u00fcdiger","family":"Ehlers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iqra","family":"Aslam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit","family":"Deshpande","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ralf","family":"Gr\u00e4fe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wissal","family":"Guedri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nour","family":"Habib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikita","family":"Maslov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Rausch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Sha","family":"Qutub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"issue":"2","key":"2186_CR1","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/JAS.2020.1003021","volume":"7","author":"Y Ma","year":"2020","unstructured":"Ma Y, Wang Z, Yang H, Yang L. Artificial intelligence applications in the development of autonomous vehicles: A survey. IEEE\/CAA J Autom Sinica. 2020;7(2):315\u201329. https:\/\/doi.org\/10.1109\/JAS.2020.1003021.","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"2186_CR2","doi-asserted-by":"crossref","unstructured":"Wang S, Anastasiu DC, Tang Z, Chang MC, Yao Y, Zheng L, Rahman MS, Arya MS, Sharma A, Chakraborty P, Prajapati S, Kong Q, Kobori N, Gochoo M, Otgonbold ME, Alnajjar F, Batnasan G, Chen PY, Hsieh JW, Wu X, Pusegaonkar SS, Wang Y, Biswas S, Chellappa R. The 8th AI city challenge. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) workshops. 2024. pp. 7261\u20137272.","DOI":"10.1109\/CVPRW63382.2024.00722"},{"issue":"3","key":"2186_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3398394","volume":"53","author":"AC Serban","year":"2021","unstructured":"Serban AC, Poll E, Visser J. Adversarial examples on object recognition: a comprehensive survey. ACM Comput Surv. 2021;53(3):1\u201338. https:\/\/doi.org\/10.1145\/3398394.","journal-title":"ACM Comput Surv"},{"key":"2186_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3179131","author":"MH Meng","year":"2022","unstructured":"Meng MH, Bai G, Teo SG, Hou Z, Xiao Y, Lin Y, et al. Adversarial robustness of deep neural networks: a survey from a formal verification perspective. IEEE Trans Dependable Secure Comput. 2022. https:\/\/doi.org\/10.1109\/TDSC.2022.3179131.","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"2186_CR5","unstructured":"Lu J, Sibai H, Fabry E, Forsyth D. No need to worry about adversarial examples in object detection in autonomous vehicles. CVPR 2017 Workshop. 2017. arxiv:1707.03501"},{"key":"2186_CR6","unstructured":"Helsch F, Aslam I, Buragohain A, Rausch A. Qualitative monitors based on the connected dependability cage approach. In: ADAPTIVE 2022: the fourteenth international conference on adaptive and self-adaptive systems and applications. Spain: IARIA, Barcelona; 2022. pp. 46\u201355. https:\/\/www.thinkmind.org\/library\/ADAPTIVE\/ADAPTIVE_2022\/adaptive_2022_2_50_50023.html."},{"key":"2186_CR7","doi-asserted-by":"publisher","unstructured":"Grieser J, Zhang M, Warnecke T, Rausch A. Assuring the safety of end-to-end learning-based autonomous driving through runtime monitoring. In: 23rd Euromicro Conference on Digital System Design (DSD 2020). Kranj, Slovenia: IEEE; 2020. pp. 476\u2013483. https:\/\/doi.org\/10.1109\/DSD51259.2020.00081.","DOI":"10.1109\/DSD51259.2020.00081"},{"key":"2186_CR8","unstructured":"UNECE World Forum for Harmonization of Vehicle Regulations: ECE\/TRANS\/WP.29\/2019\/34\/Rev.2. 2019. https:\/\/unece.org\/fileadmin\/DAM\/trans\/doc\/2020\/wp29\/ECE-TRANS-WP29-2019-34-Rev2e.pdf."},{"key":"2186_CR9","unstructured":"Cluzeau JM, Henriquel X, Rebender G, Soudain G, Dijk L, Gronskiy A, et al. Public report extract Version 1.0, European Union Aviation Safety Agency. 2020. (Concepts of design assurance for neural networks (CoDANN))."},{"key":"2186_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2312-5","volume-title":"GSN: the goal structuring notation: a structured approach to presenting arguments","author":"J Spriggs","year":"2012","unstructured":"Spriggs J. GSN: the goal structuring notation: a structured approach to presenting arguments. Heidelberg: Springer; 2012."},{"issue":"2","key":"2186_CR11","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1023\/B:FORM.0000017721.39909.4b","volume":"24","author":"K Havelund","year":"2004","unstructured":"Havelund K, Ro\u015fu G. An overview of the runtime verification tool Java PathExplorer. Formal Methods in System Des. 2004;24(2):189\u2013215. https:\/\/doi.org\/10.1023\/B:FORM.0000017721.39909.4b.","journal-title":"Formal Methods in System Des"},{"issue":"5","key":"2186_CR12","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.jlap.2008.08.004","volume":"78","author":"M Leucker","year":"2009","unstructured":"Leucker M, Schallhart C. A brief account of runtime verification. J Logic Algebraic Program. 2009;78(5):293\u2013303. https:\/\/doi.org\/10.1016\/j.jlap.2008.08.004.","journal-title":"J Logic Algebraic Program"},{"key":"2186_CR13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.4204\/EPTCS.254.2","volume":"254","author":"I Cassar","year":"2017","unstructured":"Cassar I, Francalanza A, Aceto L, Ing\u00f3lfsd\u00f3ttir A. A survey of runtime monitoring instrumentation techniques. Electronic Proc Theor Comput Sci. 2017;254:15\u201328. https:\/\/doi.org\/10.4204\/EPTCS.254.2.","journal-title":"Electronic Proc Theor Comput Sci"},{"key":"2186_CR14","doi-asserted-by":"publisher","unstructured":"Cheng CH, N\u00fchrenberg G, Yasuoka H. Runtime monitoring neuron activation patterns. In: Teich J, Fummi F (eds.) Design, automation & test in Europe conference and exhibition, DATE 2019. Florence, Italy: IEEE; 2019. pp. 300\u2013303. https:\/\/doi.org\/10.23919\/DATE.2019.8714971","DOI":"10.23919\/DATE.2019.8714971"},{"key":"2186_CR15","doi-asserted-by":"publisher","unstructured":"Henzinger TA, Lukina A, Schilling C. Outside the box: Abstraction-based monitoring of neural networks. In: 24th European Conference on Artificial Intelligence, ECAI 2020. Santiago de Compostela, Spain: IOS Press; 2020. pp. 2433\u20132440. https:\/\/doi.org\/10.3233\/FAIA200375.","DOI":"10.3233\/FAIA200375"},{"key":"2186_CR16","doi-asserted-by":"publisher","unstructured":"Hashemi V, Kret\u00ednsk\u00fd J, Rieder S, Sch\u00f6n T, Vorhoff J. Gaussian-based and outside-the-box runtime monitoring join forces. In: Runtime Verification: 24th International Conference, RV 2024. Cham: Springer; 2024. pp. 218\u2013228. https:\/\/doi.org\/10.1007\/978-3-031-74234-7_14.","DOI":"10.1007\/978-3-031-74234-7_14"},{"issue":"4","key":"2186_CR17","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MS.2001.936213","volume":"18","author":"L Sha","year":"2001","unstructured":"Sha L. Using simplicity to control complexity. IEEE Softw. 2001;18(4):20\u20138. https:\/\/doi.org\/10.1109\/MS.2001.936213.","journal-title":"IEEE Softw"},{"key":"2186_CR18","doi-asserted-by":"publisher","unstructured":"Slagel JT, White LM, Dutle A, Mu\u00f1oz CA, Crespo N. A formal verification framework for runtime assurance. In: NASA formal methods: 16th international symposium, NFM 2024. Lecture Notes in Computer Science, vol. 14627. Cham: Springer; 2024. pp. 322\u2013328. https:\/\/doi.org\/10.1007\/978-3-031-60698-4_19.","DOI":"10.1007\/978-3-031-60698-4_19"},{"key":"2186_CR19","doi-asserted-by":"publisher","unstructured":"Cofer DD, Amundson I, Sattigeri R, Passi A, Boggs C, Smith E, Gilham L, Byun T, Rayadurgam S. Run-time assurance for learning-enabled systems. In: NASA Formal Methods: 12th International Symposium, NFM 2020. Lecture Notes in Computer Science, vol. 12229. Cham: Springer; 2020. pp. 361\u2013368. https:\/\/doi.org\/10.1007\/978-3-030-55754-6_21.","DOI":"10.1007\/978-3-030-55754-6_21"},{"issue":"5","key":"2186_CR20","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1007\/s10270-023-01090-9","volume":"22","author":"MA Langford","year":"2023","unstructured":"Langford MA, Chan KH, Fleck JE, McKinley PK, Cheng BHC. MoDALAS: addressing assurance for learning-enabled autonomous systems in the face of uncertainty. Softw Syst Model. 2023;22(5):1543\u201363. https:\/\/doi.org\/10.1007\/s10270-023-01090-9.","journal-title":"Softw Syst Model"},{"key":"2186_CR21","unstructured":"Federal Aviation Administration: AC 25.1309-1B: System Design and Analysis. Advisory Circular, issued 2024-08-30. 2024. https:\/\/www.faa.gov\/regulations_policies\/advisory_circulars\/index.cfm\/go\/document.information\/documentID\/1043037."},{"issue":"10","key":"2186_CR22","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1177\/0954410011421717","volume":"226","author":"J Marzat","year":"2012","unstructured":"Marzat J, Piet-Lahanier H, Damongeot F, Walter \u00c9. Model-based fault diagnosis for aerospace systems: a survey. Proc Inst Mech Eng Part G J Aerospace Eng. 2012;226(10):1329\u201360. https:\/\/doi.org\/10.1177\/0954410011421717.","journal-title":"Proc Inst Mech Eng Part G J Aerospace Eng"},{"issue":"1","key":"2186_CR23","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","volume":"14","author":"B Khaleghi","year":"2013","unstructured":"Khaleghi B, Khamis A, Karray FO, Razavi SN. Multisensor data fusion: a review of the state-of-the-art. Inf Fusion. 2013;14(1):28\u201344. https:\/\/doi.org\/10.1016\/j.inffus.2011.08.001.","journal-title":"Inf Fusion"},{"issue":"3","key":"2186_CR24","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng D, Haase-Sch\u00fctz C, Rosenbaum L, Hertlein H, Gl\u00e4ser C, Timm F, et al. Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans Intell Transp Syst. 2021;22(3):1341\u201360. https:\/\/doi.org\/10.1109\/TITS.2020.2972974.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"Suppl 1","key":"2186_CR25","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1007\/s10462-023-10562-9","volume":"56","author":"J Gawlikowski","year":"2023","unstructured":"Gawlikowski J, Tassi CRN, Ali M, Lee J, Humt M, Feng J, et al. A survey of uncertainty in deep neural networks. Artif Intell Rev. 2023;56(Suppl 1):1513\u201389. https:\/\/doi.org\/10.1007\/s10462-023-10562-9.","journal-title":"Artif Intell Rev"},{"key":"2186_CR26","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar M, Pourpanah F, Hussain S, Rezazadegan D, Liu L, Ghavamzadeh M, et al. A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf Fusion. 2021;76:243\u201397. https:\/\/doi.org\/10.1016\/j.inffus.2021.05.008.","journal-title":"Inf Fusion"},{"key":"2186_CR27","doi-asserted-by":"publisher","unstructured":"Aslam I, Aniculaesei A, Buragohain A, Bamal D, Rausch A. Runtime safety assurance of autonomous vehicles used for last-mile delivery in urban environments. In: International Stuttgart Symposium. Springer: Wiesbaden; 2024. pp. 453\u2013470. https:\/\/doi.org\/10.1007\/978-3-658-42647-7_27.","DOI":"10.1007\/978-3-658-42647-7_27"},{"key":"2186_CR28","doi-asserted-by":"publisher","unstructured":"Aniculaesei A, Aslam I, Bamal D, Helsch F, Vorwald A, Zhang M, Rausch A. Connected dependability cage approach for safe automated driving. In: International Stuttgart Symposium. Wiesbaden: Springer; 2023. pp. 3\u201321. https:\/\/doi.org\/10.1007\/978-3-658-42048-2_1.","DOI":"10.1007\/978-3-658-42048-2_1"},{"key":"2186_CR29","unstructured":"Aslam I, Buragohain A, Bamal D, Aniculaesei A, Zhang M, Rausch A. A method for the runtime monitoring of AI-based environment perception in automated driving systems. In: ADAPTIVE 2024: the sixteenth international conference on adaptive and self-adaptive systems and applications. Venice, Italy: IARIA; 2024. https:\/\/arxiv.org\/abs\/2412.16762."},{"issue":"21","key":"2186_CR30","doi-asserted-by":"publisher","first-page":"9881","DOI":"10.3390\/app11219881","volume":"11","author":"A Rausch","year":"2021","unstructured":"Rausch A, Sedeh AM, Zhang M. Autoencoder-based semantic novelty detection: towards dependable AI-based systems. Appl Sci. 2021;11(21):9881. https:\/\/doi.org\/10.3390\/app11219881.","journal-title":"Appl Sci"},{"issue":"4","key":"2186_CR31","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s10009-023-00711-4","volume":"25","author":"K Kueffner","year":"2023","unstructured":"Kueffner K, Lukina A, Schilling C, Henzinger TA. Into the unknown: active monitoring of neural networks. Int J Softw Tools Technol Transfer. 2023;25(4):575\u201392. https:\/\/doi.org\/10.1007\/s10009-023-00711-4.","journal-title":"Int J Softw Tools Technol Transfer"},{"key":"2186_CR32","unstructured":"Qutub SS, Cihangir NK, Rosales R, Paulitsch M, Hagn K, Geissler F, Peng Y, Hinz G, Knoll AC. BEA: Revisiting anchor-based object detection DNN using budding ensemble architecture. In: 34th British Machine Vision Conference (BMVC 2023). Aberdeen, UK: BMVA Press; 2023. pp. 792\u2013797. http:\/\/proceedings.bmvc2023.org\/792\/."},{"key":"2186_CR33","doi-asserted-by":"publisher","unstructured":"Cheng CH, Luttenberger M, Yan R. Runtime monitoring DNN-based perception: Via the lens of formal methods. In: Runtime Verification. Lecture Notes in Computer Science. vol. 14245. Cham: Springer. 2023. pp. 428\u2013446. https:\/\/doi.org\/10.1007\/978-3-031-44267-4_24.","DOI":"10.1007\/978-3-031-44267-4_24"},{"key":"2186_CR34","unstructured":"Dosovitskiy A, Ros G, Codevilla F, Lopez A, Koltun V. CARLA: An open urban driving simulator. In: Levine, S., Vanhoucke, V., Goldberg, K. (eds.) Proceedings of the 1st annual conference on robot learning. proceedings of machine learning research, vol. 78. California, USA: PMLR, Mountain View; pp. 1\u201316. 2017. https:\/\/proceedings.mlr.press\/v78\/dosovitskiy17a.html."}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-02186-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-026-02186-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-026-02186-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:47:09Z","timestamp":1789717629000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-026-02186-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2186"],"URL":"https:\/\/doi.org\/10.1007\/s44163-026-02186-z","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"assertion":[{"value":"22 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"1172"}}