Sine Resistance Network-Based Motion Planning Approach for Autonomous Electric Vehicles in Dynamic Environments

Abstract

This article proposes a motion planning approach for autonomous electric vehicles to generate an appropriate planned path according to the time-varying surrounding information. This approach utilizes the proposed novel sine resistance network to mesh the road with the aim of improving the planned path smoothness, which has the capability of generating a continuous-curvature planned path that contributes to tracking and reducing the jerkiness. Meanwhile, considering that the classical artificial potential field (APF) method is only suitable for the static scenarios, a bias oval APF is constructed to predict the change of relative distance between the ego vehicle and each obstacle by taking the speed information into account. The proposed planning approach can ensure that the planned path is collision-free in dynamic environments and the generated path is smooth simultaneously. Cosimulation results in CarSim and MATLAB/Simulink are provided to prove the advantage and feasibility of the proposed motion planning approach for autonomous electric vehicles.