Path-planning in autonomous electric vehicle using nonlinear state estimation and behaviour-based controllers

Autonomous vehicle navigation in an unfamiliar environment is a challenging task. This investigation presents two algorithms for autonomous vehicle navigation in unknown environments with obstacles. Basic building blocks of the path-planning algorithms are the behaviour-based controller and nonlinear state estimator. Measurements from the sensor mounted on the vehicle are used as the input to the state estimator, whereas the estimated position of the vehicle with respect to the obstacle is the output. The estimate is then used to decide the possible control action from a family of behaviour-based controllers for navigating the vehicle. The first path-planning algorithm uses the extended Kalman filter (EKF) for estimating the vehicle position using measurements of the obstacle position. The second path-planning algorithm uses the unscented Kalman filter (UKF) to estimate thevehicle position. Our results indicate that UKF-based path-planning algorithm performs better than the EKF-based algorithm both in terms of performance and fuel consumption. This is indicated by a 9% reduction of the control effort. Path-planning algorithms presented in this investigation can be used to build reliable autonomous vehicle navigation systems. © 2017 Inderscience Enterprises Ltd.