Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars

Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars | 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 Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars Héctor Avilés, Verónica Rodríguez, Alberto Reyes, Rubén Machucho, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4651518/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 We present a comparative study of probabilistic logic factored Markov decision processes (PL-fMDPs), classification and regression trees (CART), and multilayer perceptrons (MLPs) for behavior selection in self-driving cars. While CART and MLPs are widely used in decision-making, PL-fMDPs have been recently proposed for autonomous behavior selection with promising results. We carried out three main tests to evaluate these models: (i) learning and testing with examples taken from a simulated self-driving vehicle in a race-like scenario, (ii) comparison with actions of human drivers, and (iii) navigation of a self-driving car in two adverse and unknown road scenarios. In the first and third tests, CART slightly outperformed MLPs, and both narrowly surpassed PL-fMDPs. However, PL-fMDPs showed noticeably better alignment with the decisions of human drivers in the second test, at the cost of increased learning and testing time. The results demonstrate the competitiveness of all three approaches, although the definitive superiority of any one model was not observed across all evaluation contexts. This reinforces the need to explore hybrid approaches that combine symbolic, probabilistic, and connectionist models to leverage their respective strengths and mitigate their limitations for autonomous driving in self-driving cars. Self-driving cars Factored Markov decision processes Probabilistic logic Neural networks Decision trees Full Text Additional Declarations No competing interests reported. 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-4651518","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":326430171,"identity":"3c47050f-13ab-49ff-bc05-53ccfc481b4a","order_by":0,"name":"Héctor Avilés","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Héctor","middleName":"","lastName":"Avilés","suffix":""},{"id":326430172,"identity":"0a76f58f-5214-4dd5-8c04-2f12921e02d4","order_by":1,"name":"Verónica Rodríguez","email":"","orcid":"","institution":"Technological University of the Mixteca","correspondingAuthor":false,"prefix":"","firstName":"Verónica","middleName":"","lastName":"Rodríguez","suffix":""},{"id":326430173,"identity":"4c42d35f-f872-4a1f-bc9e-2aa0ca8bb8a2","order_by":2,"name":"Alberto Reyes","email":"","orcid":"","institution":"National Institute of Electricity and Clean Energy","correspondingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Reyes","suffix":""},{"id":326430174,"identity":"f2fbd0ed-2b36-4fbb-a55b-aa90848f56dd","order_by":3,"name":"Rubén Machucho","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Rubén","middleName":"","lastName":"Machucho","suffix":""},{"id":326430175,"identity":"a372a968-4d42-40b8-bd2c-2af332d06df7","order_by":4,"name":"Marco Negrete","email":"data:image/png;base64,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","orcid":"","institution":"National Autonomous University of Mexico","correspondingAuthor":true,"prefix":"","firstName":"Marco","middleName":"","lastName":"Negrete","suffix":""},{"id":326430176,"identity":"d7c9679d-9685-4f7d-9386-e6f705153581","order_by":5,"name":"Gabriel Ramírez","email":"","orcid":"","institution":"Center for Research and Advanced Studies of the National Polytechnic Institute","correspondingAuthor":false,"prefix":"","firstName":"Gabriel","middleName":"","lastName":"Ramírez","suffix":""},{"id":326430177,"identity":"d48a48df-4bf3-4a7c-95f6-4cdc6959ed32","order_by":6,"name":"Karelly Rivera","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Karelly","middleName":"","lastName":"Rivera","suffix":""},{"id":326430178,"identity":"4c7ae29d-c259-403e-9495-9ee980799836","order_by":7,"name":"Melchor Hernández","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Melchor","middleName":"","lastName":"Hernández","suffix":""},{"id":326430179,"identity":"14802290-4186-4832-8d97-a6675ef8ceb0","order_by":8,"name":"Omar Pérez","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Omar","middleName":"","lastName":"Pérez","suffix":""},{"id":326430180,"identity":"bc5d2643-d9b3-4496-bc23-fc47c4114652","order_by":9,"name":"Gloria de la Garza","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Gloria","middleName":"de la","lastName":"Garza","suffix":""},{"id":326430181,"identity":"c3e0e578-4c22-4531-a6cb-bba52cbe30b0","order_by":10,"name":"Sergio Vázquez","email":"","orcid":"","institution":"Polytechnic University of Victoria","correspondingAuthor":false,"prefix":"","firstName":"Sergio","middleName":"","lastName":"Vázquez","suffix":""},{"id":326430182,"identity":"f4745682-9fdf-45d5-90f5-69efa4f9006a","order_by":11,"name":"Alberto Petrilli","email":"","orcid":"","institution":"Tohoku University","correspondingAuthor":false,"prefix":"","firstName":"Alberto","middleName":"","lastName":"Petrilli","suffix":""}],"badges":[],"createdAt":"2024-06-28 02:21:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4651518/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4651518/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":73122743,"identity":"62281f3d-83fb-4e93-804d-e978a38d77fe","added_by":"auto","created_at":"2025-01-07 03:01:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":627171,"visible":true,"origin":"","legend":"","description":"","filename":"AIRJ2024.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4651518/v1_covered_7d279bce-5221-402f-b4c8-84c482bc2414.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","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":"Self-driving cars, Factored Markov decision processes, Probabilistic logic, Neural networks, Decision trees","lastPublishedDoi":"10.21203/rs.3.rs-4651518/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4651518/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We present a comparative study of probabilistic logic factored Markov decision processes (PL-fMDPs), classification and regression trees (CART), and multilayer perceptrons (MLPs) for behavior selection in self-driving cars. While CART and MLPs are widely used in decision-making, PL-fMDPs have been recently proposed for autonomous behavior selection with promising results. We carried out three main tests to evaluate these models: (i) learning and testing with examples taken from a simulated self-driving vehicle in a race-like scenario, (ii) comparison with actions of human drivers, and (iii) navigation of a self-driving car in two adverse and unknown road scenarios. In the first and third tests, CART slightly outperformed MLPs, and both narrowly surpassed PL-fMDPs. However, PL-fMDPs showed noticeably better alignment with the decisions of human drivers in the second test, at the cost of increased learning and testing time. The results demonstrate the competitiveness of all three approaches, although the definitive superiority of any one model was not observed across all evaluation contexts. This reinforces the need to explore hybrid approaches that combine symbolic, probabilistic, and connectionist models to leverage their respective strengths and mitigate their limitations for autonomous driving in self-driving cars.","manuscriptTitle":"Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-19 17:55:26","doi":"10.21203/rs.3.rs-4651518/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":"0bc49ccb-5557-4e4f-b98a-1a3f06a4fd22","owner":[],"postedDate":"July 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-07T02:53:31+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-19 17:55:26","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4651518","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4651518","identity":"rs-4651518","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}