An Approach to Intelligent Traction Control Using Regression Networks and Anomaly Detection

Abstract

This article discusses an intelligent driving system (IDS) that uses a Polynomial Regression Network (PRN) and a Gaussian Anomaly Detection System (GADS). The PRN models the relation between the motor input and vehicle movement, thus, inherently taking nonlinear and noisy environmental factors into consideration. The anomaly detection system detects probable system output or sensor failure using a Gaussian pattern-match algorithm for taking proper corrective action. The time of computation for training the PRN is shown to be as low as 0.3 seconds and thus, the system can be used for instantaneous training in any environment at high speeds. Such intelligent driving systems will be useful for electric race-car designs, electric consumer vehicles, and robotic vehicles for stability on adverse road or track conditions.