Tunable and Stable Real-Time Trajectory Planning for Urban Autonomous Driving - Robotics Institute Carnegie Mellon University

Tunable and Stable Real-Time Trajectory Planning for Urban Autonomous Driving

Tianyu Gu, Jason Atwood, Chiyu Dong, John M. Dolan, and Jin-Woo Lee
Conference Paper, Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 250 - 256, September, 2015

Abstract

This paper investigates real-time on-road motion planning algorithms for autonomous passenger vehicles (APV) in urban environments, and proposed a computational efficient planning formulation. Two key properties, tunability and stability, are emphasized when designing the proposed planner. The main contributions of this paper are: 1) A computationally efficient decoupled space-time trajectory planning structure; 2) The formulation of optimization-free elastic-band-based path planning and speed-constraint-based temporal planning routines in pre-determined runtime; and 3) Identification of continuity problems with previous cost-based lattice planners that caused tunability and stability issues.

BibTeX

@conference{Gu-2015-6028,
author = {Tianyu Gu and Jason Atwood and Chiyu Dong and John M. Dolan and Jin-Woo Lee},
title = {Tunable and Stable Real-Time Trajectory Planning for Urban Autonomous Driving},
booktitle = {Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {2015},
month = {September},
pages = {250 - 256},
}