Search Results

The motion of a vehicle along a desired path is possible due to steering action of the driver. Hence, vehicle dynamics and control simulations should take into consideration the action of the driver. This work presents a preview based vehicle steering controller using Neural Networks which can be used in the vehicle lateral dynamics simulations. The training data for the Neural Network is being obtained using a steering controller from the existing literature and its gains are determined using Optimization. Three different architectures are being designed and conclusions are presented. These Neural Network models are validated by testing against real track data.

This paper uses data from a GPS/INS integrated device to investigate the feasibility of estimating vehicle states using a consumer grade GPS and INS. The GPS data is sampled at 1Hz to represent a consumer grade GPS. This data is then fused with INS data in a dual Kinematic Kalman Filter (KKF). The first KKF (yaw KKF) predicts heading angle, bias in gyroscope and sideslip angle. The second KKF (velocity KKF) predicts longitudinal and lateral velocities as well as the accelerometer biases. Due to the multirate sampling, discontinuities in the estimated states occur, hence, a line interpolation algorithm of two different orders (i.e. linear and quadratic) are implemented into the KKF. Results show that the algorithm is able to reduce the discontinuities in the velocity predictions but with an increase in error when the sideslip saturates.