Predictive Path Planning For Vehicles at Non-signalized Intersections

Files

TR Number

Date

2020-09-23

Journal Title

Journal ISSN

Volume Title

Publisher

Virginia Tech

Abstract

In the context of path planning, the non-signalized intersections are always a challenging scenario due to the mixture of traffic flow. Most path planning algorithms use the information at the current time instance to generate an optimal path. Because of the dynamics of the non-signalized intersections, iteratively generating a path in a high frequency is necessary, resulting in an enormous waste of computational resources. Rapidly-exploring Random Tree (RRT) as an effective local path planning methodology can determine a feasible path in the static environment. Few improvements are proposed to adopt the RRT to the non-signalized intersections. Gaussian Processes Regression (GPR) is used to predict the other vehicles' future location. The location information in the current and future time instance is used to generate a probability position map. The map not only avoids useless sampling procedures but also increases the speed of generating a path. The optimal steering strategy is deployed to guarantee the trajectory is collision-free in both current and future time frames. Overall, the proposed probabilistic RRT algorithm can select a collision-free path in the non-signalized intersections by combining the GPR, probability position map, and optimal-steering.

Description

Keywords

path planning, autonomous vehicle, motion planning

Citation

Collections