Abstract
This article presents a novel estimator based on sensor fusion, which combines the Neural Network (NN) with a Kalman filter in order to estimate the vehicle roll angle. The NN estimates a “pseudo-roll angle” through variables that are easily measured from Inertial Measurement Unit (IMU) sensors. An IMU is a device that is commonly used for vehicle motion detection, and its cost has decreased during recent years. The pseudo-roll angle is introduced in the Kalman filter in order to filter noise and minimize the variance of the norm and maximum errors’ estimation. The NN has been trained for J-turn maneuvers, double lane change maneuvers and lane change maneuvers at different speeds and road friction coefficients. The proposed method takes into account the vehicle non-linearities, thus yielding good roll angle estimation. Finally, the proposed estimator has been compared with one that uses the suspension deflections to obtain the pseudo-roll angle. Experimental results show the effectiveness of the proposed NN and Kalman filter-based estimator.
Highlights
Recent developments in vehicle technology have steered the industry towards an increase in vehicle safety, and it is considered to be one of the key features of a vehicle, even at the initial design stages
We propose a novel estimator based on a Neural Network (NN) combined with a Kalman filter in order to estimate the vehicle roll angle
This article presents a novel estimator based on sensor fusion, which combines NN and Linear Kalman Filter (LKF) in order to estimate the vehicle roll angle
Summary
Recent developments in vehicle technology have steered the industry towards an increase in vehicle safety, and it is considered to be one of the key features of a vehicle, even at the initial design stages. Suspension deflection sensors are expensive, so real-time measurement of the roll angle is typically not available for vehicles [11]. For this reason, different algorithms based on the fusion of other types of sensors are proposed. We propose a novel estimator based on a Neural Network (NN) combined with a Kalman filter in order to estimate the vehicle roll angle (see Figure 1). The estimator architecture is formed by two modules: the NN module and the Kalman module The former estimates a pseudo-roll angle, and the latter filters the noise and minimizes the norm and maximum errors.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
