Page 310 - Kỷ yếu hội thảo khoa học lần thứ 12 - Công nghệ thông tin và Ứng dụng trong các lĩnh vực (CITA 2023)

294

Implement Performance Evaluation for Scheduling

Algorithms used in Autonomous Driving Vehicles

Tran-Viet An and Vu-Anh-Quang Nguyen [0000-00003-3604-397X]

Vietnam-Korea University of Information and Communication Technology, Da Nang, Viet Nam
nvaquang@vku.udn.vn

Abstract. With the increasing popularity of autonomous driving vehicles, the
development of efficient scheduling algorithms that can make real-time decisions
for vehicle operations has become crucial. In this paper, we propose a model for

EBAND algorithms used in autonomous driving vehicles. We will build a
simulation platform to test these algorithms and compare their performance based
on various metrics, such as path length, task completion time. The results of the
performance evaluation will help to identify the strengths and weaknesses of each
algorithm and provide insights into their suitability for different applications.

Keywords: Gazebo, scheduling, Autonomous Car, path planning.

1 Introduction

The development of autonomous driving vehicles (ADVs) has brought significant
changes to the transportation industry. With the increasing demand for efficient and
safe operation of autonomous vehicles, scheduling algorithms play a crucial role in
making real-time decisions for vehicle operations. In this paper, we focus on the per-

gorithms, used in autonomous driving vehicles. These algorithms are responsible for
tasks, such as route planning, traffic management, and collision avoidance [1].
ADVs have gained significant attention in recent years due to their potential to rev-
olutionize the transportation industry. One of the key challenges in developing these
vehicles is designing efficient and effective scheduling algorithms for navigating com-
plex environments. Various algorithms, such as A*, Dijkstra's, and EBAND, have been
proposed and implemented in autonomous driving vehicles.
The goal of this paper is to build a model and implement a performance evaluation
of these scheduling algorithms in the context of autonomous driving vehicles. The pa-
per presents an overview of the algorithms and their underlying principles, as well as a
description of the evaluation framework used in the study. The results of the evaluation
are then presented and analyzed, providing insights into the strengths and suitability of
each algorithm.
The remainder of the paper is organized as follows. Section 2 provides an overview
of the scheduling algorithms used in ADVs and describes the evaluation framework

CITA 2023 ISBN: 978-604-80-8083-9