Comparative Evaluation of Deep Learning Models for Small-Scale Autonomous Driving Under Embedded System Constraints
Proceedings of Engineering and Technology Innovation · 03.08.2026 · 34 · 33-46
DOI: 10.46604/peti.2026.16240 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of Engineering and Technology Innovation, online erschienen am 03.08.2026. Verfasst von Korawit Krajangpan und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This study compares vision-based autonomous driving models for small-scale vehicles under embedded resource constraints. Three architectures—a linear model, a categorical model, and a convolutional neural network (CNN) 3D Model—are evaluated on the DonkeyCar platform. Training data comprise over 23,000 front-facing images with control commands, which are collected through joystick-based teleoperation. Model performance is benchmarked using quantitative metrics (mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R²)) and driving tests using Raspberry Pi 4. The CNN 3D model achieves the highest prediction accuracy, whereas the linear model provides more stable driving with lower computational cost. The findings indicate that model performance and hardware limits must be considered when selecting models for embedded applications: the linear model is suitable for resource-constrained platforms requiring real-time stability, the categorical model suits discrete decision-making, and the CNN 3D model supports accuracy-prioritized tasks with greater computing capacity.
Zitieren
APA
Krajangpan, K., & Petsri, K. (2026). Comparative Evaluation of Deep Learning Models for Small-Scale Autonomous Driving Under Embedded System Constraints. Proceedings of Engineering and Technology Innovation, 34, 33-46. https://doi.org/10.46604/peti.2026.16240
Vancouver
Krajangpan K, Petsri K. Comparative Evaluation of Deep Learning Models for Small-Scale Autonomous Driving Under Embedded System Constraints. Proceedings of Engineering and Technology Innovation. 2026;34:33-46. doi:10.46604/peti.2026.16240
BibTeX
@article{Krajangpan2026,
author = {Krajangpan, Korawit and Petsri, Kittinan},
title = {Comparative Evaluation of Deep Learning Models for Small-Scale Autonomous Driving Under Embedded System Constraints},
journal = {Proceedings of Engineering and Technology Innovation},
year = {2026},
volume = {34},
pages = {33--46},
doi = {10.46604/peti.2026.16240}
}
EUVIMED