Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-augmented Automation for Real Driving Prediction: an Industrial Use Case

Romina Eramo, Hamzeh Eyal Salman, Matteo Spezialetti, Darko Stern, Pierre Quinton, Antonio Cicchetti

TL;DR

Real-world RDE testing is time-consuming and expensive; the paper demonstrates an AI-augmented approach combining Machine Learning and Model-based Engineering to synthesize a high-fidelity driving simulator from historical real-driving data for virtual performance testing. It proposes a conceptual AIDOaRt framework that integrates Observe/Analyze/Automate capabilities to support continuous vehicle development and applies it to the AVL RDE use case, targeting improved emissions predictions. Experimental results show data-driven driver-behavior models, particularly RandomForest and DecisionTree, achieving about 92% accuracy across 15 speed-classes, enabling faster, cheaper, and more scalable testing in automotive development. The work highlights practical impact for industry by enabling continuous integration of driving-emission predictions into development pipelines and sets a path toward more complete digital twins and metamodels for driver behavior.

Abstract

The risen complexity of automotive systems requires new development strategies and methods to master the upcoming challenges. Traditional methods need thus to be changed by an increased level of automation, and a faster continuous improvement cycle. In this context, current vehicle performance tests represent a very time-consuming and expensive task due to the need to perform the tests in real driving conditions. As a consequence, agile/iterative processes like DevOps are largely hindered by the necessity of triggering frequent tests. This paper reports on a practical experience of developing an AI-augmented solution based on Machine Learning and Model-based Engineering to support continuous vehicle development and testing. In particular, historical data collected in real driving conditions is leveraged to synthesize a high-fidelity driving simulator and hence enable performance tests in virtual environments. Based on this practical experience, this paper also proposes a conceptual framework to support predictions based on real driving behavior.

AI-augmented Automation for Real Driving Prediction: an Industrial Use Case

TL;DR

Real-world RDE testing is time-consuming and expensive; the paper demonstrates an AI-augmented approach combining Machine Learning and Model-based Engineering to synthesize a high-fidelity driving simulator from historical real-driving data for virtual performance testing. It proposes a conceptual AIDOaRt framework that integrates Observe/Analyze/Automate capabilities to support continuous vehicle development and applies it to the AVL RDE use case, targeting improved emissions predictions. Experimental results show data-driven driver-behavior models, particularly RandomForest and DecisionTree, achieving about 92% accuracy across 15 speed-classes, enabling faster, cheaper, and more scalable testing in automotive development. The work highlights practical impact for industry by enabling continuous integration of driving-emission predictions into development pipelines and sets a path toward more complete digital twins and metamodels for driver behavior.

Abstract

The risen complexity of automotive systems requires new development strategies and methods to master the upcoming challenges. Traditional methods need thus to be changed by an increased level of automation, and a faster continuous improvement cycle. In this context, current vehicle performance tests represent a very time-consuming and expensive task due to the need to perform the tests in real driving conditions. As a consequence, agile/iterative processes like DevOps are largely hindered by the necessity of triggering frequent tests. This paper reports on a practical experience of developing an AI-augmented solution based on Machine Learning and Model-based Engineering to support continuous vehicle development and testing. In particular, historical data collected in real driving conditions is leveraged to synthesize a high-fidelity driving simulator and hence enable performance tests in virtual environments. Based on this practical experience, this paper also proposes a conceptual framework to support predictions based on real driving behavior.
Paper Structure (24 sections, 5 equations, 4 figures, 4 tables)

This paper contains 24 sections, 5 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Basic concepts
  4. The AIDOaRt approach
  5. The Real Driving Emissions case
  6. Real Driving Prediction framework
  7. Model
  8. Prediction
  9. Data
  10. Driving behaviour
  11. Application to the RDE case
  12. Data Acquisition
  13. Features Selection
  14. Pre-processing
  15. Driving Behaviour Prediction
  16. ...and 9 more sections

Figures (4)

  • Figure 1: AIDOaRt approach
  • Figure 2: AVL Route Studio Simulator architecture.
  • Figure 3: Example of speed profile for a selected route (real driving in blue, simulated speed in yellow)
  • Figure 5: Performance results of several classifiers.