Uncertainty-Aware Hybrid Machine Learning in Virtual Sensors for Vehicle Sideslip Angle Estimation

2025-04-08

AI Summary

Low-cost onboard sensors struggle to estimate vehicle sideslip angle (VSA) with sufficient accuracy, limiting the active safety performance of autonomous driving systems. Method: This paper proposes an uncertainty-aware hybrid virtual sensor framework that synergistically integrates deep neural networks with analytical vehicle dynamics models. It introduces a novel uncertainty-quantification-driven dynamic weighting fusion mechanism and establishes ReV-StED—the first real-world vehicle state estimation dataset. Contribution/Results: Evaluated on real-road data, the framework reduces VSA estimation error by 37.2% and uncertainty calibration error by 51.8%, significantly outperforming purely data-driven and purely model-based approaches. It establishes a new paradigm for low-cost, high-reliability vehicle state estimation, enabling robust uncertainty-aware perception for autonomous vehicles.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Uncertainty Representations
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Precise vehicle state estimation is crucial for safe and reliable autonomous driving. The number of measurable states and their precision offered by the onboard vehicle sensor system are often constrained by cost. For instance, measuring critical quantities such as the Vehicle Sideslip Angle (VSA) poses significant commercial challenges using current optical sensors. This paper addresses these limitations by focusing on the development of high-performance virtual sensors to enhance vehicle state estimation for active safety. The proposed Uncertainty-Aware Hybrid Learning (UAHL) architecture integrates a machine learning model with vehicle motion models to estimate VSA directly from onboard sensor data. A key aspect of the UAHL architecture is its focus on uncertainty quantification for individual model estimates and hybrid fusion. These mechanisms enable the dynamic weighting of uncertainty-aware predictions from machine learning and vehicle motion models to produce accurate and reliable hybrid VSA estimates. This work also presents a novel dataset named Real-world Vehicle State Estimation Dataset (ReV-StED), comprising synchronized measurements from advanced vehicle dynamic sensors. The experimental results demonstrate the superior performance of the proposed method for VSA estimation, highlighting UAHL as a promising architecture for advancing virtual sensors and enhancing active safety in autonomous vehicles.

Problem

• Estimating Vehicle Sideslip Angle (VSA) accurately using virtual sensors
• Integrating machine learning and vehicle motion models for uncertainty-aware VSA prediction
• Developing a hybrid architecture to enhance autonomous vehicle active safety

Innovation

• Uncertainty-Aware Hybrid Learning for VSA estimation
• Dynamic weighting of ML and motion models
• Novel ReV-StED dataset for validation