Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control

The use of Deep Learning algorithms in the domain of Decision Making for Autonomous Vehicles has garnered significant attention in the literature in recent years, showcasing considerable potential. Nevertheless, most of the solutions proposed by the scientific community encounter difficulties in rea...

Full description

Saved in:
Bibliographic Details
Main Authors: Rodrigo Gutiérrez-Moreno, Rafael Barea, Elena López-Guillén, Felipe Arango, Fabio Sánchez-García, Luis M. Bergasa
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/1/117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850071810164391936
author Rodrigo Gutiérrez-Moreno
Rafael Barea
Elena López-Guillén
Felipe Arango
Fabio Sánchez-García
Luis M. Bergasa
author_facet Rodrigo Gutiérrez-Moreno
Rafael Barea
Elena López-Guillén
Felipe Arango
Fabio Sánchez-García
Luis M. Bergasa
author_sort Rodrigo Gutiérrez-Moreno
collection DOAJ
description The use of Deep Learning algorithms in the domain of Decision Making for Autonomous Vehicles has garnered significant attention in the literature in recent years, showcasing considerable potential. Nevertheless, most of the solutions proposed by the scientific community encounter difficulties in real-world applications. This paper aims to provide a realistic implementation of a hybrid Decision Making module in an Autonomous Driving stack, integrating the learning capabilities from the experience of Deep Reinforcement Learning algorithms and the reliability of classical methodologies. Our Decision Making system is in charge of generating steering and velocity signals using the HD map information and sensors pre-processed data. This work encompasses the implementation of concatenated scenarios in simulated environments, and the integration of Autonomous Driving modules. Specifically, the authors address the Decision Making problem by employing a Partially Observable Markov Decision Process formulation and offer a solution through the use of Deep Reinforcement Learning algorithms. Furthermore, an additional control module to execute the decisions in a safe and comfortable way through a hybrid architecture is presented. The proposed architecture is validated in the CARLA simulator by navigating through multiple concatenated scenarios, outperforming the CARLA Autopilot in terms of completion time, while ensuring both safety and comfort.
format Article
id doaj-art-1fc818fc019b4787977ed0a809f55322
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-1fc818fc019b4787977ed0a809f553222025-08-20T02:47:13ZengMDPI AGSensors1424-82202024-12-0125111710.3390/s25010117Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical ControlRodrigo Gutiérrez-Moreno0Rafael Barea1Elena López-Guillén2Felipe Arango3Fabio Sánchez-García4Luis M. Bergasa5Electronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainElectronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainElectronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainElectronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainElectronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainElectronics Departament, University of Alcalá (UAH), 28805 Alcalá de Henares, Madrid, SpainThe use of Deep Learning algorithms in the domain of Decision Making for Autonomous Vehicles has garnered significant attention in the literature in recent years, showcasing considerable potential. Nevertheless, most of the solutions proposed by the scientific community encounter difficulties in real-world applications. This paper aims to provide a realistic implementation of a hybrid Decision Making module in an Autonomous Driving stack, integrating the learning capabilities from the experience of Deep Reinforcement Learning algorithms and the reliability of classical methodologies. Our Decision Making system is in charge of generating steering and velocity signals using the HD map information and sensors pre-processed data. This work encompasses the implementation of concatenated scenarios in simulated environments, and the integration of Autonomous Driving modules. Specifically, the authors address the Decision Making problem by employing a Partially Observable Markov Decision Process formulation and offer a solution through the use of Deep Reinforcement Learning algorithms. Furthermore, an additional control module to execute the decisions in a safe and comfortable way through a hybrid architecture is presented. The proposed architecture is validated in the CARLA simulator by navigating through multiple concatenated scenarios, outperforming the CARLA Autopilot in terms of completion time, while ensuring both safety and comfort.https://www.mdpi.com/1424-8220/25/1/117autonomous drivingdeep reinforcement learningdecision-makingvehicle controlCARLA simulator
spellingShingle Rodrigo Gutiérrez-Moreno
Rafael Barea
Elena López-Guillén
Felipe Arango
Fabio Sánchez-García
Luis M. Bergasa
Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
Sensors
autonomous driving
deep reinforcement learning
decision-making
vehicle control
CARLA simulator
title Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
title_full Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
title_fullStr Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
title_full_unstemmed Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
title_short Enhancing Autonomous Driving in Urban Scenarios: A Hybrid Approach with Reinforcement Learning and Classical Control
title_sort enhancing autonomous driving in urban scenarios a hybrid approach with reinforcement learning and classical control
topic autonomous driving
deep reinforcement learning
decision-making
vehicle control
CARLA simulator
url https://www.mdpi.com/1424-8220/25/1/117
work_keys_str_mv AT rodrigogutierrezmoreno enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol
AT rafaelbarea enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol
AT elenalopezguillen enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol
AT felipearango enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol
AT fabiosanchezgarcia enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol
AT luismbergasa enhancingautonomousdrivinginurbanscenariosahybridapproachwithreinforcementlearningandclassicalcontrol