The estimation of vehicle handling and control parameters in dynamic conditions is challenging due to errors and delays in real-time data logging with low-resolution onboard sensors. These issues significantly impact the performance of vehicle stability and control algorithms, particularly in vehicles under testing. This study presents error mapping concept parallel to statistical error method for real-time vehicle state estimation that addresses the limitations of low-resolution sensors with errors and delays in measured signal.
In this study, a real-time (RT) model is developed and trained with in-house electric SUV to estimate yaw velocity and slip angle. The model leverages other measured signals available from the vehicle’s onboard sensor setup. It integrates an error and delay function with error predictive model to estimate the targeted parameter signal response in real time. The RT model introduces an error function method that enhances prediction accuracy by combining the error map value with the error weight of the target signal. The error function for the target signal filters systematic and trend errors from vehicle measurement data, accounting for vehicle specifications and environmental conditions. The error model generalizes to predict target signal errors under various maneuvers. Model training and error mapping is iterative, have performed using on-track test logs from two data sources. In each iteration, the error map is refined by assigning error weights to parameters, making the model adaptive to evolve error characteristics in future training sessions. This process can enhance the model's accuracy and reliability across different driving conditions. The initial model validation has been performed with ISO ramp steer and ISO chirp tests, demonstrate the direction and scope for enhancing real-time vehicle state estimation using error map function at lower cost.