A Novel Hybrid XAI Solution for Autonomous Vehicles: Real-Time Interpretability Through LIME–SHAP Integration
Sensors · 22.10.2024 · 24 (21) · 6776
DOI: 10.3390/s24216776 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.10.2024. Verfasst von H Ahmed Tahir und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Engineering and Mathematics, Western Sydney University, Penrith, NSW 2751, Australia. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah bint Abdulrahman University.
Abstract (Originalsprache)
The rapid advancement in self-driving and autonomous vehicles (AVs) integrated with artificial intelligence (AI) technology demands not only precision but also output transparency. In this paper, we propose a novel hybrid explainable AI (XAI) framework that combines local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP). Our framework combines the precision and globality of SHAP and low computational requirements of LIME, creating a balanced approach for onboard deployment with enhanced transparency. We evaluate the proposed framework on three different state-of-the-art models: ResNet-18, ResNet-50, and SegNet-50 on the KITTI dataset. The results demonstrate that our hybrid approach consistently outperforms traditional approaches by achieving a fidelity rate of more than 85%, interpretability factor of more than 80%, and consistency of more than 70%, surpassing the conventional methods. Furthermore, the inference time of our proposed framework with ResNet-18 was 0.28 s; for ResNet-50, it was 0.571 s; and that for SegNet was 3.889 s with XAI layers. This is optimal for onboard computations and deployment. This research establishes a strong foundation for the deployment of XAI in safety-critical AV with balanced tradeoffs for real-time decision-making.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computing, Engineering and Mathematics, Western Sydney University, Penrith, NSW 2751, Australia.
- Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh P.O. Box 84428, Saudi Arabia.
- Department of Mathematics, Government College University, Lahore 54000, Pakistan.
- Department of Artificial Intelligence and Robotics, Sejong University, Seoul 05006, Republic of Korea.
ORCID-Profile: Walaa Alayed, Waqar Ul Hassan, Amir Haider
Förderung
- Princess Nourah bint Abdulrahman University
Zitieren
APA
Tahir, H. A., Alayed, W., Hassan, W. U., & Haider, A. (2024). A Novel Hybrid XAI Solution for Autonomous Vehicles: Real-Time Interpretability Through LIME–SHAP Integration. Sensors, 24(21), 6776. https://doi.org/10.3390/s24216776
Vancouver
Tahir HA, Alayed W, Hassan WU, Haider A. A Novel Hybrid XAI Solution for Autonomous Vehicles: Real-Time Interpretability Through LIME–SHAP Integration. Sensors. 2024;24(21):6776. doi:10.3390/s24216776
BibTeX
@article{Tahir2024,
author = {Tahir, H Ahmed and Alayed, Walaa and Hassan, Waqar Ul and Haider, Amir},
title = {A Novel Hybrid XAI Solution for Autonomous Vehicles: Real-Time Interpretability Through LIME–SHAP Integration},
journal = {Sensors},
year = {2024},
volume = {24},
number = {21},
pages = {6776},
doi = {10.3390/s24216776}
}
EUVIMED