(Pontificia Universidad Católica del Perú, 2018-10-17) Grebner, Anna-Maria Stephanie; Reger, Johann
Navigation and obstacle avoidance are important tasks in the research field of au- tonomous mobile
robots. The challenge tackled in this work is the navigation of a 4- wheeled car-type robot to a
desired parking position while avoiding obstacles on the way. The taken approach to solve this
problem is based on neural fuzzy techniques.
Earlier works resulted in a controller to navigate the robot in a clear environment. It is extended
by considering additional parameters in the training process. The learning method used in this
training is dynamic backpropagation.
For the obstacle avoidance problem an additional neuro-fuzzy controller is set up and trained. It
influences the results from the navigation controller to avoid collisions with objects blocking the
path. The controller is trained with dynamic backpropagation and
a reinforcement learning algorithm called deep deterministic policy gradient.
