Speed Planning for an Autonomous Vehicle with Conflict Moving Objects

Abstract

One challenging problem about autonomous vehicles (AV) is to optimize vehicle trajectories with considering the conflict moving objects (e.g. left and right turns, car following). This paper investigates an AV speed planning problem where the AV follows a given spatial path and the possible conflict regions of the moving objects are known. This problem converts the two-dimensional (2D) trajectory planning problem to a one-dimensional (1D) speed planning problem that decides the optimal speeds and accelerations of the AV along the spatial path. This paper first analyzes the feasibility region of the AV movements for a general conflict avoidance application (e.g., following a car, or passing an intersection). This analysis reveals the upper and lower bounds for a feasible trajectory. With that, a customized dynamic-programming- (DP)-based algorithm is developed to solve the optimal trajectory. In the end, a numerical experiment is conducted to demonstrate the performance of the customized DP-based algorithm. The result shows that the proposed model and algorithm can solve the studied speed planning problem effectively.