Two-Lane Path Planning of Autonomous Vehicles in 2.5D Environments

Riku Usami, Yuji Kobashi, Taiki Onuma, Takashi Maekawa

Research output: Contribution to journalArticle

Abstract

We present a two-lane path planning of autonomous vehicles in two-and-a-half-dimensional (2.5D) environments. Our method builds on collision-free two-dimensional (2D) path-planning techniques from our previous work, and extends these techniques to 2.5D by mapping a 2D path in the parameter space onto a terrain graph surface, as a curve on the surface in the object space. Based on this path on the terrain surface, we propose a novel method of designing cross slopes in high curvature regions of the path, such that vehicles need not slow down in these regions. Furthermore, we apply time-optimal control techniques developed in robotics to compute the minimal-time speed control along the specified path. Examples are provided to demonstrate the effectiveness of the proposed algorithm.

Original languageEnglish
Article number8911549
Pages (from-to)281-293
Number of pages13
JournalIEEE Transactions on Intelligent Vehicles
Volume5
Issue number2
DOIs
Publication statusPublished - 2020 Jun
Externally publishedYes

Keywords

  • autonomous vehicles
  • B-spline curves
  • haul road
  • path planning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Automotive Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'Two-Lane Path Planning of Autonomous Vehicles in 2.5D Environments'. Together they form a unique fingerprint.

Cite this