Abstract
Automated vehicles represent a rapidly expanding global market, drawing significant attention from both industry and academia. However, existing solutions often lack transparency, particularly in the disclosure of architectural designs, resulting in fragmented development approaches. To address these gaps, this paper introduces a novel, modular reference architecture tailored for Level 2 Automated Driving Systems (ADS). The proposed architecture ensures safety, scalability, and adaptability across diverse vehicle platforms. A comprehensive validation is conducted using OpenPilot, an open-source Level 2 ADS implementation, demonstrating the architecture's practical feasibility in achieving reliable control tasks under real-time constraints. This work bridges the gap between industrial and academic contributions, offering actionable insights and a robust foundation for future advancements in ADS development.
| Original language | English |
|---|---|
| Article number | e70050 |
| Number of pages | 19 |
| Journal | Expert Systems |
| Volume | 42 |
| Issue number | 6 |
| Early online date | 5 May 2025 |
| DOIs | |
| Publication status | Published - Jun 2025 |
Bibliographical note
Copyright © 2025 The Author(s). Expert Systems published by John Wiley & Sons Ltd. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.Funding
This work was funded by the UKRI EPSRC EP/Y028813/1 ‘National Edge AI Hub for Real Data: Edge Intelligence for Cyber-disturbances and Data Quality’.
Keywords
- ADAS
- automated driving system
- knowledge-based system
- performance evaluation
- system architecture