The automotive industry has been continuously evolving and improving in recent years, moving towards autonomous driving. The aim is to minimize human errors by integrating vehicles with Advanced Driver Assistance Systems (ADASs). These systems enhance driving safety and improve travel comfort. The most advanced ADASs represent the latest steps towards fully autonomous driving. However, to make these new ADASs more effective and efficient, it is necessary to increase the amount of data available to them. This will enhance their ability to analyze the vehicle's surroundings and respond accordingly. To achieve this, new developments in this field are leveraging technologies and systems that facilitate communication between vehicles on the road and fixed sensors on the infrastructure that monitor those roads. These new systems are primarily developed and tested for collision avoidance and accident prevention. These new systems are initially tested in digital driving simulations. Testing and simulations in virtual environments have become an essential tool in the research and development of new automotive technologies. They allow the creation of any possible scenario and enable continuous modifications to the project, replicating real-world occurrences numerous times, thus speeding up testing, preventing potential errors, and reducing costs. This thesis leverages the potential of simulations in virtual environments to create an ADAS that allows the vehicle to avoid collisions and accidents in situations of poor visibility for the driver. This system is designed by exploring the collaboration and communication between the vehicle and the infrastructure, thereby collecting more data that enables the vehicle to make more efficient decisions to ensure safety. This thesis concretizes the work by examining the results obtained during the simulations, evaluating the impact of communication delays between the vehicle and infrastructure on the system's effectiveness, and analyzing the actual efficiency of the system in preventing collisions.
L’industria automobilistica negli ultimi anni sta cambiando e migliorando in continuazione, puntando verso la guida autonoma. Il mondo del veicolo sta sempre più eliminando gli errori umani alla guida, integrando le auto con Sistemi Avanzati di Guida Assistita (Autonomous Driver Advanced System, ADASs). Questi permettono all’uomo di guidare in maggiore sicurezza andando anche a migliorare il confort quando si viaggia. Gli ADASs più moderni rappresentano gli ultimi passi verso quella che un giorno sarà la guida completamente autonoma. Per poter rendere questi nuovi ADASs più performanti ed efficienti è necessario però aumentare i dati a loro disposizione. Così che siano più capaci di analizzare la situazione in cui il veicolo si trova e reagire di conseguenza. Per fare ciò i nuovi sviluppi in questo ambito sfruttano tecnologie e sistemi che mettano in comunicazione i veicoli sulla strada con i sensori fisse sulle infrastrutture che monitorano quelle strade. Questi nuovi sistemi vengono sviluppati e sperimentati soprattutto per quello che riguarda prevenzioni alle collisioni e agli incidenti. Questi nuovi sistemi vengono sempre prima sperimentati in simulazioni di guida digitali. I test e le simulazioni in ambienti virtuali rappresentano ormai uno strumento imprescindibile nella ricerca e nello sviluppo di nuove tecnologie nel mondo dell’automobile. Danno la possibilità di creare qualsiasi possibile scenario e permettono di portare continue modifiche al progetto continuando a riprodurre innumerevoli volte ciò che accadrebbe nella realtà, velocizzando però i test, prevenendo possibili errori e riducendo i costi. Questo lavoro di tesi sfrutta il potenziale delle simulazioni in ambienti virtuali per creare un ADAS che permetta al veicolo di evitare collisioni e incidenti in situazioni di scarsa visibilità per il guidatore. Questo sistema è progettato esplorando la collaborazione e comunicazione tra veicolo e infrastrutture, raccogliendo così più dati che permettano al veicolo di prendere decisioni più efficienti al fine di mettere il veicolo in condizioni di sicurezza. Questa tesi concretizza il lavoro fatto esaminando i risultati ottenuti durante le simulazioni, valutando l’influenza dei ritardi di comunicazione tra veicolo e infrastrutture sull’efficacia del sistema, e analizzando la reale efficienza del sistema nell’evitare collisioni.
Design of an ADAS for blind intersections leveraging I2V communication
FRIGERIO, EMANUELE
2023/2024
Abstract
The automotive industry has been continuously evolving and improving in recent years, moving towards autonomous driving. The aim is to minimize human errors by integrating vehicles with Advanced Driver Assistance Systems (ADASs). These systems enhance driving safety and improve travel comfort. The most advanced ADASs represent the latest steps towards fully autonomous driving. However, to make these new ADASs more effective and efficient, it is necessary to increase the amount of data available to them. This will enhance their ability to analyze the vehicle's surroundings and respond accordingly. To achieve this, new developments in this field are leveraging technologies and systems that facilitate communication between vehicles on the road and fixed sensors on the infrastructure that monitor those roads. These new systems are primarily developed and tested for collision avoidance and accident prevention. These new systems are initially tested in digital driving simulations. Testing and simulations in virtual environments have become an essential tool in the research and development of new automotive technologies. They allow the creation of any possible scenario and enable continuous modifications to the project, replicating real-world occurrences numerous times, thus speeding up testing, preventing potential errors, and reducing costs. This thesis leverages the potential of simulations in virtual environments to create an ADAS that allows the vehicle to avoid collisions and accidents in situations of poor visibility for the driver. This system is designed by exploring the collaboration and communication between the vehicle and the infrastructure, thereby collecting more data that enables the vehicle to make more efficient decisions to ensure safety. This thesis concretizes the work by examining the results obtained during the simulations, evaluating the impact of communication delays between the vehicle and infrastructure on the system's effectiveness, and analyzing the actual efficiency of the system in preventing collisions.File | Dimensione | Formato | |
---|---|---|---|
2024_07_Frigerio.pdf
accessibile in internet per tutti
Descrizione: Testo della Tesi
Dimensione
4.69 MB
Formato
Adobe PDF
|
4.69 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/223694