Reliable State Estimation in a Truck-Semitrailer Combination using an Artificial Neural Network-Aided Extended Kalman Filter

TL;DR

This paper introduces a hybrid Extended Kalman Filter that combines neural network estimates with traditional filtering to reliably estimate the state of a truck-semitrailer, even under unknown loading conditions.

Contribution

It presents the first analysis of estimator generalization for semitrailers and proposes a novel hybrid EKF that improves accuracy and robustness over existing methods.

Findings

H-EKF outperforms standard EKF and pure ANN estimators in experiments.

The hybrid approach maintains reliable estimates across varying payload conditions.

Experimental results demonstrate improved accuracy in estimating articulation angle and tire forces.

Abstract

Advanced driver assistance systems are critically dependent on reliable and accurate information regarding a vehicles' driving state. For estimation of unknown quantities, model-based and learning-based methods exist, but both suffer from individual limitations. On the one hand, model-based estimation performance is often limited by the models' accuracy. On the other hand, learning-based estimators usually do not perform well in "unknown" conditions (bad generalization), which is particularly critical for semitrailers as their payload changes significantly in operation. To the best of the authors' knowledge, this work is the first to analyze the capability of state-of-the-art estimators for semitrailers to generalize across "unknown" loading states. Moreover, a novel hybrid Extended Kalman Filter (H-EKF) that takes advantage of accurate Artificial Neural Network (ANN) estimates while preserving reliable generalization capability is presented. It estimates the articulation angle between truck and semitrailer, lateral tire forces and the truck steering angle utilizing sensor data of a standard semitrailer only. An experimental comparison based on a full-scale truck-semitrailer combination indicates the superiority of the H-EKF compared to a state-of-the-art extended Kalman filter and an ANN estimator.