Bridging Data-Driven and Physics-Based Models: A Consensus Multi-Model Kalman Filter for Robust Vehicle State Estimation

2025-06-15

AI Summary

Vehicle state estimation must balance physical interpretability with the capacity to model complex nonlinear dynamics; however, standalone physics-based or data-driven models exhibit insufficient robustness under critical conditions (e.g., aggressive turning, low-friction surfaces). To address this, we propose a Consensus Multi-Model Kalman Filtering (CMMKF) framework that innovatively integrates physics-informed and data-driven models within a unified estimation architecture, incorporating a dynamic reliability weighting scheme. We further introduce a novel covariance propagation strategy based on Koopman operator linearization and ensemble methods, enabling cross-model unified uncertainty quantification without requiring pre-training. A consensus fusion mechanism ensures enhanced state estimate consistency. Experimental validation on an electric all-wheel-drive Chevrolet Equinox demonstrates that, compared to single-model baselines, CMMKF reduces average position and attitude estimation errors by 32.7%, while significantly improving robustness under challenging driving scenarios.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Vehicle state estimation presents a fundamental challenge for autonomous driving systems, requiring both physical interpretability and the ability to capture complex nonlinear behaviors across diverse operating conditions. Traditional methodologies often rely exclusively on either physics-based or data-driven models, each with complementary strengths and limitations that become most noticeable during critical scenarios. This paper presents a novel consensus multi-model Kalman filter framework that integrates heterogeneous model types to leverage their complementary strengths while minimizing individual weaknesses. We introduce two distinct methodologies for handling covariance propagation in data-driven models: a Koopman operator-based linearization approach enabling analytical covariance propagation, and an ensemble-based method providing unified uncertainty quantification across model types without requiring pretraining. Our approach implements an iterative consensus fusion procedure that dynamically weighs different models based on their demonstrated reliability in current operating conditions. The experimental results conducted on an electric all-wheel-drive Equinox vehicle demonstrate performance improvements over single-model techniques, with particularly significant advantages during challenging maneuvers and varying road conditions, confirming the effectiveness and robustness of the proposed methodology for safety-critical autonomous driving applications.

Problem

• Integrating physics-based and data-driven models for vehicle state estimation
• Handling covariance propagation in data-driven models effectively
• Improving robustness in autonomous driving under diverse conditions

Innovation

• Consensus multi-model Kalman filter framework
• Koopman operator-based linearization for covariance
• Ensemble-based unified uncertainty quantification