Non-myopic Trajectory Planning for Autonomous Driving Combining Single-Query and Multi-Query Methods
Jaekyung Cho, Sihyeon Jo, Seung‐Woo Seo, Seong-Woo Kim · 2022
Motion planning for autonomous driving in a dynamic environment is challenging in considering safety, efficiency, and passenger comfort. We clarify some scenarios in which previous multi-query motion planning methods demonstrate inefficient results, such as unnecessarily returning to the reference path and time delays due to myopic behavior. We propose a novel two-step method to address the problems. The myopic trajectory planning step uses an optimization method with the Frenet frame to generate exhaustive trajectory candidates on a very limited time horizon, which considers vehicle kinematics and dynamic safety. The non-myopic trajectory planning step uses variation in the rapidly exploring random tree to find the expected fastest trajectory to reach a local goal position among the results of the previous step. In 16.2% of entire random scenarios, our proposed method reduces the time to reach a destination by more than a 5% performance gap compared to other state-of-the-art motion planning methods.