Focusing on autonomous driving algorithm development, this paper proposes a novel real-time trajectory planner formulated as a Nonlinear Model Predictive Control (NMPC) algorithm. The mathematical formulation of the problem is deeply reported and discussed. The numerical solution of the NMPC problem is the result of a novel genetic algorithm strategy that represents the innovative aspect of the work proposed. The aim of this paper is also to show how genetic algorithm can be a valid approach for motion planning strategies. Numerical results are discussed through simulations that show a reasonable behaviour of the proposed strategy in the presence of moving obstacles as well as in a wide range of road friction conditions. Moreover, a real-time implementation for research purposes is assumed as possible by considering computational time analysis reported.

MPC trajectory planner for autonomous driving solved by genetic algorithm technique

Arrigoni S.;Braghin F.;Cheli F.
2021

Abstract

Focusing on autonomous driving algorithm development, this paper proposes a novel real-time trajectory planner formulated as a Nonlinear Model Predictive Control (NMPC) algorithm. The mathematical formulation of the problem is deeply reported and discussed. The numerical solution of the NMPC problem is the result of a novel genetic algorithm strategy that represents the innovative aspect of the work proposed. The aim of this paper is also to show how genetic algorithm can be a valid approach for motion planning strategies. Numerical results are discussed through simulations that show a reasonable behaviour of the proposed strategy in the presence of moving obstacles as well as in a wide range of road friction conditions. Moreover, a real-time implementation for research purposes is assumed as possible by considering computational time analysis reported.
autonomous driving
GA methods
motion planning
MPC
obstacle avoidance
File in questo prodotto:
File Dimensione Formato  
MPC trajectory planner for autonomous driving solved by genetic algorithm technique.pdf

Accesso riservato

: Publisher’s version
Dimensione 4.75 MB
Formato Adobe PDF
4.75 MB Adobe PDF   Visualizza/Apri
11311-1203702_Arrigoni.pdf

embargo fino al 18/12/2022

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 12.28 MB
Formato Adobe PDF
12.28 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1203702
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact