Motion planning for autonomous driving with a conformal spatiotemporal lattice

We present a motion planner for autonomous highway driving that adapts the state lattice framework pioneered for planetary rover navigation to the structured environment of public roadways. The main contribution of this paper is a search space representation that allows the search algorithm to systematically and efficiently explore both spatial and temporal dimensions in real time. This allows the low-level trajectory planner to assume greater responsibility in planning to follow a leading vehicle, perform lane changes, and merge between other vehicles. We show that our algorithm can readily be accelerated on a GPU, and demonstrate it on an autonomous passenger vehicle.

I. INTRODUCTION

A viable autonomous passenger vehicle must be able to plot a precise and safe trajectory through busy traffic while observing the rules of the road and minimizing risk due to unexpected events such as sudden braking or swerving by another vehicle, or the incursion of a pedestrian or animal onto the road. The planner must be able to produce a plan within a small fixed time window. In this paper we are concerned with the production of precise short-term plans of the vehicle location, valid for the next several seconds.