Fuzzy Model Predictive Control for Collision Avoidance Control of Autonomous Vehicles

  • Shaowen Hao
  • , Yimin Chen
  • , Jian Gao
  • , Hunhui He
  • , Yazhou Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Driving safety is essential in collision avoidance control of autonomous vehicles. Considering the nonlinear vehicle dynamic model and the road obstacles, it is challenging to avoid collisions and maintain vehicle motion in the presence of road obstacles. This paper proposes an improved fuzzy model predictive control algorithm for autonomous vehicles to avoid possible collisions. The nonlinear vehicle systems are expressed as weighted sum of linear affine models via the Takagi-Sugeno fuzzy approach, which reduces the computational cost and maintain control accuracy for guaranteeing the collision avoidance performances. Simulation results show the proposed algorithm can successfully avoid multiple obstacles with low computational complexity.

Original languageEnglish
Title of host publicationIntelligent Transportation Engineering - Proceedings of the 9th International Conference, ICITE 2024
EditorsGuoqiang Mao
PublisherIOS Press BV
Pages267-277
Number of pages11
ISBN (Electronic)9781643686028
DOIs
StatePublished - 17 Jul 2025
Event9th International Conference on Intelligent Transportation Engineering, ICITE 2024 - Xi'an, China
Duration: 18 Oct 202420 Oct 2024

Publication series

NameAdvances in Transdisciplinary Engineering
Volume72
ISSN (Print)2352-751X
ISSN (Electronic)2352-7528

Conference

Conference9th International Conference on Intelligent Transportation Engineering, ICITE 2024
Country/TerritoryChina
CityXi'an
Period18/10/2420/10/24

Keywords

  • Autonomous vehicles
  • collision avoidance
  • fuzzy MPC

Fingerprint

Dive into the research topics of 'Fuzzy Model Predictive Control for Collision Avoidance Control of Autonomous Vehicles'. Together they form a unique fingerprint.

Cite this