EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving

Daniel Yordanov, Ashim Chakraborty iD, Md Mahmudul Hasan, Silvia Cirstea iD

Sensors · 19.12.2024 · 24 (24) · 8099

DOI: 10.3390/s24248099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.12.2024. Verfasst von Daniel Yordanov und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing and Information Science, Anglia Ruskin University, Cambridge CB1 1PT, UK. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Improving the ability of autonomous vehicles to accurately identify and follow lanes in various contexts is crucial. This project aims to provide a novel framework for optimizing a self-driving vehicle that can detect lanes and steer accordingly. A virtual sandbox environment was developed in Unity3D that provides a semi-automated procedural road and driving generation framework for a variety of road scenarios. Four types of segments replicate actual driving situations by directing the car using strategically positioned waypoints. A training dataset thus generated was used to train a behavioral driving model that employs a convolutional neural network to detect the lane and ensure that the car steers autonomously to remain within lane boundaries. The model was evaluated on real-world driving footage from Comma.ai, exhibiting an autonomy of 77% in low challenge road conditions and of 66% on roads with sharper turns.

Schlagwörter

Stichwörter der Autor:innen

Unity3Dautonomous steeringdeep learning

Autor:innen und Institutionen

  • School of Computing and Information Science, Anglia Ruskin University, Cambridge CB1 1PT, UK.

ORCID-Profile: Ashim Chakraborty, Silvia Cirstea

Zitieren

APA

Yordanov, D., Chakraborty, A., Hasan, M. M., & Cirstea, S. (2024). A Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving. Sensors, 24(24), 8099. https://doi.org/10.3390/s24248099

Vancouver

Yordanov D, Chakraborty A, Hasan MM, Cirstea S. A Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving. Sensors. 2024;24(24):8099. doi:10.3390/s24248099

BibTeX
@article{Yordanov2024,
  author = {Yordanov, Daniel and Chakraborty, Ashim and Hasan, Md Mahmudul and Cirstea, Silvia},
  title = {A Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {8099},
  doi = {10.3390/s24248099}
}
Kostenlos starten →