• Home
  •  >
  • Robotica
  •  >
  • Volume 30
  •  >
  • Issue 02
  •  >
  • Optimal motion planning by reinforcement learning in autonomous mobile vehicles

Robotica

Table of Contents - March 2012 - Volume 30, Issue 02  

Articles

Optimal motion planning by reinforcement learning in autonomous mobile vehicles

M. Gómeza1 c1, R. V. Gonzáleza1, T. Martínez-Marína2, D. Meziata1 and S. Sáncheza1

a1 Departamento de Automática, Escuela Politécnica Superior, Universidad de Alcalá, Campus Universitario, 28871 Alcalá de Henares, Madrid, Spain

a2 Departamento de Física, Ingeniería de Sistemas y Teoría de la Señal, Universidad de Alicante, 03080 Alicante, Spain

SUMMARY

The aim of this work has been the implementation and testing in real conditions of a new algorithm based on the cell-mapping techniques and reinforcement learning methods to obtain the optimal motion planning of a vehicle considering kinematics, dynamics and obstacle constraints. The algorithm is an extension of the control adjoining cell mapping technique for learning the dynamics of the vehicle instead of using its analytical state equations. It uses a transformation of cell-to-cell mapping in order to reduce the time spent during the learning stage. Real experimental results are reported to show the satisfactory performance of the algorithm.

(Received April 04 2011)

(Accepted April 13 2011)

(Online publication May 19 2011)

KEYWORDS:

  • Adjoining;
  • Cell-mapping;
  • Non-holonomic systems;
  • Optimal motion planning;
  • Reinforcement learning

Correspondence:

c1 Corresponding author. E-mail: mgomez@aut.uah.es