-
Renan P. Vieira
Programa de Pós-Graduação em Engenharia Eletrônica, Departamento de Engenharia Eletrônica e de Telecomunicações, Universidade do Estado do Rio de Janeiro, RJ
-
Téo C. Revoredo, IEEE Member
Departamento de Engenharia Eletrônica e de Telecomunicações, Universidade do Estado do Rio de Janeiro, RJ
Keywords:
Path planning, Autonomous parking, polynomial Parametrization, Optimization, Genetic algorithm, Path tracking, Pybullet
Abstract
Vehicle parking maneuvers in large cities have a great influence on traffic flow, measures that minimize time and space spent on these maneuvers are of great value. As a starting point, one must plan the best way to carry out parking, a non-trivial task with regard to non-holonomic vehicles prevalent in large metropolises. Based on this scenario, this work presents a path planning algorithm to park a car based on polynomial parameterization optimized by genetic algorithm. The objective is to define a law of motion to steer the vehicle from an initial pose near a parking space to a final pose within the latter smoothly, without interruption, avoiding any obstacles on the way. Path tracking is performed via pure pursuit controller. Results are presented in a 3D physical simulation environment and compared with another approach present in the literature, demonstrating its usefulness and providing the basis for broader studies.
