Double Gradient Method: a New Optimization Method for the Trajectory Optimization Problem.

EasyChair Preprint 11507

Abstract

In this paper, a new optimization method for the trajectory optimization problem is presented. This new method allows to predict racing lines described by cubic splines (problems solved by stochastic methods in most cases) in times like deterministic methods. The proposed Double Gradient Method (DGM) is not affected by the problem dimensionality. Comparing the results with real professional drivers collected data showed that the DGM is reliable for lap time simulations with race line optimization, being applicable for help drivers find the fastest racing line, for embedded algorithms development or for autonomous vehicle competitions.

Keyphrases: Autonomous Racing Vehicle, Lap Time Simulation, Optimization

@booklet{EasyChair:11507,
  author    = {Alam Rosato Macêdo and Ebrahim Samer El Youssef and Marcus V. Americano da Costa},
  title     = {Double Gradient Method: a New Optimization Method for the Trajectory Optimization Problem.},
  howpublished = {EasyChair Preprint 11507},
  year      = {EasyChair, 2023}}