Runtime-Bounded Tunable Motion Planning for Autonomous Driving - Robotics Institute Carnegie Mellon University

Runtime-Bounded Tunable Motion Planning for Autonomous Driving

Tianyu Gu, John M. Dolan, and Jin-Woo Lee
Conference Paper, Proceedings of IEEE Intelligent Vehicles Symposium (IV '16), pp. 1301 - 1306, June, 2016

Abstract

Trajectory planning methods for on-road autonomous driving are commonly formulated to optimize a Single Objective calculated by accumulating Multiple Weighted Feature terms (SOMWF). Such formulation typically suffers from the lack of planning tunability. Two main causes are the lack of physical intuition and relative feature prioritization due to the complexity of SOMWF, especially when the number of features is big. This paper addresses this issue by proposing a framework with multiple tunable phases of planning, along with two novel techniques: 1) Optimization-free trajectory smoothing/nudging; 2) Sampling-based trajectory search with cascaded ranking.

BibTeX

@conference{Gu-2016-26520,
author = {Tianyu Gu and John M. Dolan and Jin-Woo Lee},
title = {Runtime-Bounded Tunable Motion Planning for Autonomous Driving},
booktitle = {Proceedings of IEEE Intelligent Vehicles Symposium (IV '16)},
year = {2016},
month = {June},
pages = {1301 - 1306},
keywords = {autonomous driving, motion planning, tunability},
}