[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119562-en":3,"doc-seo-119562-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119562,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Robust Trajectory Forecasting for Autonomous Vehicles using Conformal Machine Learning - Master’s Thesis in Automation and Control Engineering","Safety in autonomous driving depends on accurate trajectory predictions and trustworthy uncertainty estimates for surrounding traffic agents. This master’s thesis studies rigorous uncertainty quantification for trajectory forecasting of autonomous heavy vehicle combinations in highway environments, where black-box machine learning can degrade under out-of-distribution inputs. It investigates and extends conformal prediction methods to build statistically valid prediction regions with guaranteed coverage. Adaptive extensions incorporate heuristic uncertainty or time-series modeling online to improve robustness during distribution shifts. Closed-loop evaluation integrates prediction regions into an MPC-based planner to enable safer downstream trajectory decisions.","Robust Trajectory Forecasting for Autonomous Vehicles using Conformal Machine Learning  \nTesi di Laurea Magistrale in  \nAutomation and Control Engineering  \nAuthor: Marco Lodetti  \nStudent ID: 224760  \nAdvisor: Prof. Sergio M. Savaresi Co-advisors:  \nAcademic Year: 2024-2025  \ni  \nAbstract  \nEnsuring safety in autonomous driving requires not only accurate predictions of surrounding traffic agents but also reliable quantification of the uncertainty associated with those predictions. This thesis addresses the problem of rigorous uncertainty quantification in trajectory forecasting for autonomous heavy vehicle combinations operating in highway environments. In such safety-critical scenarios, black-box machine learning models often suffer from performance degradation due to out-of-distribution inputs, which can lead to unsafe path planning decisions if not properly accounted for.  \nTo tackle this, we investigate and extend a family of methods known as conformal prediction: a model-agnostic framework that wraps around any trajectory predictor and constructs prediction regions with guaranteed statistical coverage, without assuming specific data distributions. The project analyzes state-of-the-art conformal methods for both finite and infinite-horizon control settings, with focus on their empirical performance in simulated highway scenarios. We propose novel extensions that embed heuristic uncertainty or leverage time-series modeling to adapt prediction sets online, improving coverage under distribution shifts.  \nThese methods are tested in a closed-loop autonomous truck simulator, where predicted regions are integrated with a model predictive controller (MPC) responsible for generating safe and feasible paths. This MPC integration is not the focus of the research, but is instead used as a case study to demonstrate how quantified uncertainty can inform downstream planning.  \nResults show that the novel adaptive conformal methods maintain coverage under challenging and changing traffic configurations and produce uncertainty bounds that are more reliable than those based on heuristic methods. This work enables downstream systems, such as path planners, to better handle prediction uncertainty with formal guarantees, closing the gap between learning-based forecasting and robust motion planning.  \nKeywords: Conformal Prediction, Uncertainty Quantification, Trajectory Forecasting, Machine Learning, Autonomous Driving, Model Predictive Control.  \niii  \nAbstract in lingua italiana  \nGarantire la sicurezza nella guida autonoma richiede non solo una previsione accurata del comportamento dei veicoli circostanti, ma anche una stima affidabile dell’incertezza associata a tali previsioni. Questa tesi affronta il problema della quantificazione rigorosadell’incertezza nella previsione delle traiettorie per veicoli pesanti autonomi operanti inscenari autostradali. In contesti così critici, i modelli di Machine Learning tendono aperdere affidabilità quando vengono utilizzati in scenari diversi da quelli osservati durante la fase di addestramento, il che può compromettere la sicurezza della pianificazione della traiettoria se l’incertezza non viene adeguatamente considerata.  \nPer affrontare questo problema, vengono analizzati e potenziati metodi appartenenti alla famiglia della Conformal Prediction (CP): un approccio agnostico rispetto al modellopredittivo, capace di fornire regioni predittive con garanzie statistiche di copertura, indipendentemente dalla distribuzione dei dati. Il lavoro si concentra sull’analisi empirica di metodi avanzati di CP, sia per orizzonti temporali finiti che infiniti, valutandonele prestazioni in scenari autostradali simulati. Sono inoltre proposte estensioni di talimetodi che incorporano euristiche o modelli autoregressivi per adattare dinamicamentele regioni predittive, migliorando la copertura in condizioni di Distribution Shifts. Talimetodi vengono integrati in un simulatore closed-loop per la guida autonoma di camion,","cbCaibwHk2Oz9CWy","https://ap.wps.com/l/cbCaibwHk2Oz9CWy","pdf",7035668,1,141,"English","en",105,"# Abstract\n## Overview\n## Conformal prediction methods\n## Online adaptation and evaluation\n## Closed-loop MPC integration\n# Keywords\n# Acknowledgments","[{\"question\":\"Why is uncertainty quantification important for trajectory forecasting in autonomous driving?\",\"answer\":\"Accurate predictions alone are not enough in safety-critical highway scenarios. Uncertainty must be quantified reliably so planning can account for prediction errors and out-of-distribution inputs.\"},{\"question\":\"What approach does the thesis use to provide reliable uncertainty estimates?\",\"answer\":\"The thesis investigates conformal prediction, a model-agnostic framework that wraps around trajectory predictors and constructs prediction regions with guaranteed statistical coverage.\"},{\"question\":\"How are the conformal prediction results used during autonomous driving evaluation?\",\"answer\":\"Predicted regions are integrated into a model predictive controller (MPC) within a closed-loop autonomous truck simulator to generate safe and feasible paths.\"}]","Robust Trajectory Forecasting for Autonomous Vehicles using Conformal Machine Learning - Master’s Thesis in Automation and Control Engineering | PDF",1785724991,355,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"robust-trajectory-forecasting-for-autonomous-vehicles-using-conformal-machine-learning-masters-thesis-in-automation-and-control-engineering","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/robust-trajectory-forecasting-for-autonomous-vehicles-using-conformal-machine-learning-masters-thesis-in-automation-and-control-engineering/119562/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is uncertainty quantification important for trajectory forecasting in autonomous driving?","Question",{"text":75,"@type":76},"Accurate predictions alone are not enough in safety-critical highway scenarios. Uncertainty must be quantified reliably so planning can account for prediction errors and out-of-distribution inputs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What approach does the thesis use to provide reliable uncertainty estimates?",{"text":80,"@type":76},"The thesis investigates conformal prediction, a model-agnostic framework that wraps around trajectory predictors and constructs prediction regions with guaranteed statistical coverage.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the conformal prediction results used during autonomous driving evaluation?",{"text":84,"@type":76},"Predicted regions are integrated into a model predictive controller (MPC) within a closed-loop autonomous truck simulator to generate safe and feasible paths.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]