S-AI-ROBOTICS : A Sparse Artificial Intelligence Architecture with Hormonal Orchestration, Parsimonious Control, and Symbolic Memory for Adaptive, Safe, and Explainable Embodied Robotics

S-AI-ROBOTICS : A Sparse Artificial Intelligence Architecture with Hormonal Orchestration, Parsimonious Control, and Symbolic Memory for Adaptive, Safe, and Explainable Embodied Robotics | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article S-AI-ROBOTICS : A Sparse Artificial Intelligence Architecture with Hormonal Orchestration, Parsimonious Control, and Symbolic Memory for Adaptive, Safe, and Explainable Embodied Robotics said slaoui This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9234313/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Robotic systems increasingly operate in dynamic, uncertain, and resource-constrained environments, where safety, energy efficiency, and explainability are as critical as raw performance. While learning-based and monolithic control architectures have demonstrated impressive capabilities, they often rely on continuous activation, data-intensive training, and opaque decision processes, making them fragile, energy-demanding, and difficult to audit in safety-critical contexts. This paper introduces S-AI-ROBOTICS , a bio-inspired and modular robotic intelligence framework grounded in the principles of Sparse Artificial Intelligence (S-AI) . The proposed architecture departs from always-on robotic control by enforcing context-aware parsimony , where specialized robotic agents are activated only when justified by a symbolic hormonal state reflecting urgency, stability, energy, and confidence. A Robo-MetaAgent orchestrates agent activation through constrained optimization and hysteresis-based dynamics, ensuring stable and frugal behavior selection under competing objectives. To regulate behavioral priorities, S-AI-ROBOTICS integrates an artificial hormonal signaling layer , inspired by neuroendocrine systems, which modulates agent thresholds through bounded emission, inhibition, diffusion, and decay mechanisms. In parallel, a symbolic and contextual memory subsystem stores behavioral engrams—linking hormonal context, activated agents, actions, and outcomes—enabling rapid recall, adaptation, and native explainability of robotic decisions. The framework is evaluated using SAI-UT+ , a reproducible experimental testbench, across multi-scenario robotic tasks including navigation, obstacle avoidance, energy scarcity, sensor degradation, and emergency handling. Results demonstrate that S-AI-ROBOTICS achieves improved stability, reduced energy consumption, and enhanced explainability compared to classical control, behavior trees, and reinforcement learning baselines, while maintaining robust performance under uncertainty. By unifying hormonal regulation, sparse orchestration, and symbolic memory within an embodied intelligence framework, S-AI-ROBOTICS establishes a principled foundation for adaptive, safe, and explainable robotic systems. Artificial Intelligence and Machine Learning Sparse Artificial Intelligence S-AI-ROBOTICS Bio-inspired robotics Hormonal signaling Sparse orchestration Modular multi-agent systems Hysteresis-based control Symbolic memory Behavioral engrams Explainable robotics Energy-efficient systems Autonomous robotics Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9234313","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":612689085,"identity":"943d70b5-506f-4d27-a110-ddf85d1e8bf5","order_by":0,"name":"said slaoui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYHACxgNAgoefgYH9A9F6wFokGxjYiLcGpIXB4ACxWuQb2B8c+FFxWMb4Rnba4woGO3kGscMP8GoxOMBjcLDnzGEesxu52w3PMCQbNkinGeDXwsDDcIC3DaxlA9A/zAkM0gn4tYAcdvAvUIvxDLCWeqCWdAIhd4DB4DDIFgOJ3G1ALYeBWnIIOAyo+LDMmXQeiTNvNxs2GBw3bJPOKcDvsPb2hw/fVFjb87fnbnzYUFEtzy+dvgG/w5hRLWUgJUJHwSgYBaNgFOACABX1QgIXA026AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0001-6900-8102","institution":"Mohammed V university","correspondingAuthor":true,"prefix":"","firstName":"said","middleName":"","lastName":"slaoui","suffix":""}],"badges":[],"createdAt":"2026-03-26 12:50:42","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9234313/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9234313/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105538713,"identity":"b06471f0-f4c7-4498-86a9-f6554b88450c","added_by":"auto","created_at":"2026-03-27 07:44:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":702296,"visible":true,"origin":"","legend":"","description":"","filename":"SlaouiSAIRoboticsVersionII.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9234313/v1_covered_9ff1fbe4-f160-4199-9937-aa8b42f3ba69.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eS-AI-ROBOTICS : A Sparse Artificial Intelligence Architecture with Hormonal Orchestration, Parsimonious Control, and Symbolic Memory for Adaptive, Safe, and Explainable Embodied Robotics\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Mohammed V University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Sparse Artificial Intelligence, S-AI-ROBOTICS, Bio-inspired robotics, Hormonal signaling, Sparse orchestration, Modular multi-agent systems, Hysteresis-based control, Symbolic memory, Behavioral engrams, Explainable robotics, Energy-efficient systems, Autonomous robotics","lastPublishedDoi":"10.21203/rs.3.rs-9234313/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9234313/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRobotic systems increasingly operate in dynamic, uncertain, and resource-constrained environments, where safety, energy efficiency, and explainability are as critical as raw performance. While learning-based and monolithic control architectures have demonstrated impressive capabilities, they often rely on continuous activation, data-intensive training, and opaque decision processes, making them fragile, energy-demanding, and difficult to audit in safety-critical contexts. This paper introduces \u003cstrong\u003eS-AI-ROBOTICS\u003c/strong\u003e, a bio-inspired and modular robotic intelligence framework grounded in the principles of \u003cstrong\u003eSparse Artificial Intelligence (S-AI)\u003c/strong\u003e. The proposed architecture departs from always-on robotic control by enforcing \u003cstrong\u003econtext-aware parsimony\u003c/strong\u003e, where specialized robotic agents are activated only when justified by a symbolic hormonal state reflecting urgency, stability, energy, and confidence. A \u003cstrong\u003eRobo-MetaAgent\u003c/strong\u003e orchestrates agent activation through constrained optimization and hysteresis-based dynamics, ensuring stable and frugal behavior selection under competing objectives. To regulate behavioral priorities, S-AI-ROBOTICS integrates an \u003cstrong\u003eartificial hormonal signaling layer\u003c/strong\u003e, inspired by neuroendocrine systems, which modulates agent thresholds through bounded emission, inhibition, diffusion, and decay mechanisms. In parallel, a \u003cstrong\u003esymbolic and contextual memory subsystem\u003c/strong\u003e stores behavioral engrams—linking hormonal context, activated agents, actions, and outcomes—enabling rapid recall, adaptation, and native explainability of robotic decisions. The framework is evaluated using \u003cstrong\u003eSAI-UT+\u003c/strong\u003e, a reproducible experimental testbench, across multi-scenario robotic tasks including navigation, obstacle avoidance, energy scarcity, sensor degradation, and emergency handling. Results demonstrate that S-AI-ROBOTICS achieves improved stability, reduced energy consumption, and enhanced explainability compared to classical control, behavior trees, and reinforcement learning baselines, while maintaining robust performance under uncertainty. By unifying hormonal regulation, sparse orchestration, and symbolic memory within an embodied intelligence framework, S-AI-ROBOTICS establishes a principled foundation for adaptive, safe, and explainable robotic systems.\u003c/p\u003e","manuscriptTitle":"S-AI-ROBOTICS : A Sparse Artificial Intelligence Architecture with Hormonal Orchestration, Parsimonious Control, and Symbolic Memory for Adaptive, Safe, and Explainable Embodied Robotics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-27 07:44:08","doi":"10.21203/rs.3.rs-9234313/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"64f237b6-8e0a-4edd-8691-c34f542ec658","owner":[],"postedDate":"March 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65194235,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-27T07:44:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-27 07:44:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9234313","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9234313","identity":"rs-9234313","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}