Optimizing Autonomous Vehicle Performance Using Improved Proximal Policy Optimization
Sensors · 20.03.2025 · 25 (6) · 1941
DOI: 10.3390/s25061941 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.03.2025. Verfasst von Mehmet Bilban und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Technologies, Necmettin Erbakan University, 42360 Seydişehir, Turkey. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Selcuk University Scientific Research Coordinatorship.
Abstract (Originalsprache)
Autonomous vehicles must make quick and accurate decisions to operate efficiently in complex and dynamic urban traffic environments, necessitating a reliable and stable learning mechanism. The proximal policy optimization (PPO) algorithm stands out among reinforcement learning (RL) methods for its consistent learning process, ensuring stable decisions under varying conditions while avoiding abrupt deviations during execution. However, the PPO algorithm often becomes trapped in a limited search space during policy updates, restricting its adaptability to environmental changes and alternative strategy exploration. To overcome this limitation, we integrated Lévy flight’s chaotic and comprehensive exploration capabilities into the PPO algorithm. Our method helped the algorithm explore larger solution spaces and reduce the risk of getting stuck in local minima. In this study, we collected real-time data such as speed, acceleration, traffic sign positions, vehicle locations, traffic light statuses, and distances to surrounding objects from the CARLA simulator, processed via Apache Kafka. These data were analyzed by both the standard PPO and our novel Lévy flight-enhanced PPO (LFPPO) algorithm. While the PPO algorithm offers consistency, its limited exploration hampers adaptability. The LFPPO algorithm overcomes this by combining Lévy flight’s chaotic exploration with Apache Kafka’s real-time data streaming, an advancement absent in state-of-the-art methods. Tested in CARLA, the LFPPO algorithm achieved a 99% success rate compared to the PPO algorithm’s 81%, demonstrating superior stability and rewards. These innovations enhance safety and RL exploration, with the LFPPO algorithm reducing collisions to 1% versus the PPO algorithm’s 19%, advancing autonomous driving beyond existing techniques.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Technologies, Necmettin Erbakan University, 42360 Seydişehir, Turkey.
- Computer Engineering, Faculty of Technology, Selçuk University, 42140 Konya, Turkey.
ORCID-Profile: Mehmet Bilban, Onur İnan
Förderung
- Selcuk University Scientific Research Coordinatorship
Zitieren
APA
Bilban, M., & İnan, O. (2025). Optimizing Autonomous Vehicle Performance Using Improved Proximal Policy Optimization. Sensors, 25(6), 1941. https://doi.org/10.3390/s25061941
Vancouver
Bilban M, İnan O. Optimizing Autonomous Vehicle Performance Using Improved Proximal Policy Optimization. Sensors. 2025;25(6):1941. doi:10.3390/s25061941
BibTeX
@article{Bilban2025,
author = {Bilban, Mehmet and İnan, Onur},
title = {Optimizing Autonomous Vehicle Performance Using Improved Proximal Policy Optimization},
journal = {Sensors},
year = {2025},
volume = {25},
number = {6},
pages = {1941},
doi = {10.3390/s25061941}
}
EUVIMED