Simultaneous Estimation of Vehicle Roll and Sideslip Angles through a Deep Learning Approach

Abstract

<jats:p>Presently, autonomous vehicles are on the rise and are expected to be on the roads in the coming years. In this sense, it becomes necessary to have adequate knowledge about its states to design controllers capable of providing adequate performance in all driving scenarios. Sideslip and roll angles are critical parameters in vehicular lateral stability. The later has a high impact on vehicles with an elevated center of gravity, such as trucks, buses, and industrial vehicles, among others, as they are prone to rollover. Due to the high cost of the current sensors used to measure these angles directly, much of the research is focused on estimating them. One of the drawbacks is that vehicles are strong non-linear systems that require specific methods able to tackle this feature. The evolution in Artificial Intelligence models, such as the complex Artificial Neural Network architectures that compose the Deep Learning paradigm, has shown to provide excellent performance for complex and non-linear control problems. In this paper, the authors propose an inexpensive but powerful model based on Deep Learning to estimate the roll and sideslip angles simultaneously in mass production vehicles. The model uses input signals which can be obtained directly from onboard vehicle sensors such as the longitudinal and lateral accelerations, steering angle and roll and yaw rates. The model was trained using hundreds of thousands of data provided by Trucksim® and validated using data captured from real driving maneuvers using a calibrated ground truth device such as VBOX3i dual-antenna GPS from Racelogic®. The use of both Trucksim® software and the VBOX measuring equipment is recognized and widely used in the automotive sector, providing robust data for the research shown in this article.</jats:p>

Hyperparameter Optimization Techniques for Designing Software Sensors Based on Artificial Neural Networks

“…Comparing state estimators in automotive applications, trial and error, Grid Search or Random Search approaches seem to be commonly used. These approaches promise a simple implementation and first insight into the feasibility [6][7][8][9]. In this paper, optimization methods of different complexity are compared.…”

Estimation of Vehicle Attitude, Acceleration, and Angular Velocity Using Convolutional Neural Network and Dual Extended Kalman Filter

“…Several recent studies have also been conducted to estimate the vehicle roll and pitch angle using neural network. In [ 25 , 26 , 27 ], the vehicle roll angle estimation method using sensor fusion with a neural network and Kalman filter was proposed. Furthermore, a vehicle roll and road bank angle estimation method based on a deep neural network was introduced [ 28 ].…”

Sensors and Sensor’s Fusion in Autonomous Vehicles

“…The latter has a high impact on vehicles with an elevated center of gravity, such as trucks, buses, and industrial vehicles, among others, as they are prone to rollover. Due to the high cost of the current sensors used to measure these angles directly, González, L.P. et al, in their work [ 7 ], proposed an inexpensive but powerful model based on deep learning to estimate the roll and sideslip angles simultaneously in mass production vehicles. The model uses input signals which can be obtained directly from onboard vehicle sensors, such as longitudinal and lateral accelerations, steering angle and roll and yaw rates.…”