Obstacle Avoidance Path Design for Autonomous Vehicles – A Review

Ahmed Tijani
Additional contact information
Ahmed Tijani: The University of Toledo, Toledo, Ohio, USA

Technium, 2021, vol. 3, issue 5, 64-81

Abstract: Abstract. Autonomous vehicles are the new revolution in the transportation system. They are designed to improve road efficiency and driving safety. Much research has been undertaken over the years involving significant topics, such as autonomous driving stages and safety, road formation control, obstacle detection, and obstacle avoidance strategies. The implementation of an autonomous driving system relies on several stages. Therefore, a range of different planning approaches are required to ensure safety, comfort, and efficiency. The safety aspect is one of the challenges in self-driving cars as it allows autonomous cars to navigate on the roads. Obstacle detection and obstacle avoidance systems have a major impact on autonomous driving safety. Obstacle detection utilizes the Markov random field (MRF) model that combines three potentials to segment obstacles and non-obstacles in a hazardous environment. Obstacle avoidance applies an improved artificial potential field algorithm to create a collision-free path for autonomous vehicles. In this paper, several methods and approaches are discussed for autonomous vehicles obstacle detection and avoidance systems as well as vehicle platooning and formation control techniques. A large number of relevant published papers have been systematically reviewed. Obstacle detection methods and obstacle avoidance approaches for autonomous vehicles are summarized. The results illustrate the efficiency of applied models in optimizing and improving a safe navigating path for autonomous vehicles.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://techniumscience.com/index.php/technium/article/view/3810 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tec:techni:ojs:3810

Access Statistics for this article

Technium is currently edited by Scurtu Ionut Cristian

More articles in Technium from Technium Science
Bibliographic data for series maintained by Ana Maria Golita ().