Autonomous Parallel Parking of Four Wheeled
Vehicles Utilizing Adoptive Fuzzy – Neuro
Control System
Jerome T. Marasigan, Iara Marie B. Saberon, Dan Patrick B. San Jose, Paul Anthony T. Sevilla
Argel A. Bandala
Department of Electronics and Communications Engineering
De La Salle University, Manila
Abstract — The study presents an autonomous sensor
based parallel parking maneuver on a car-like mobile
robot. This project focuses on parallel parking the
car-like mobile robot within a given scenario
following the fifth degree polynomial reference path
in a backward maneuver. Training data, gathered
from the fifth degree polynomial path, is subjected to
subtractive clustering algorithm to determine the
fuzzy controller and trained by the adaptive neuro-
fuzzy inference system. The project uses eight
ultrasonic sensors, placed strategically to avoid radial
imprecision, to detect the obstacles along its path; an
accelerometer is also used to detect the inclination of
the car-like mobile robot (CLMR). The sensors
acquire necessary sensor data for the Neuro-Fuzzy
Inference System to determine the proper motion
direction at each sampling point. The efficiency of the
proposed Neuro-Fuzzy Controller (NFC) design is
revealed through the actual results.
Keywords - Neuro - Fuzzy, Autonomous Parallel
Parking, Adoptive Network
I. INTRODUCTION
Drivers, in general, find it hard to plan a
precise path on parallel parking. Drivers do not
have precise measurements in order to control their
parking motions. Nonetheless, they still become
skillful at executing complicated tasks through
experience, common sense and training in pursuing
imprecise rules that can be translated in the form of
“If…Then…”. These “If…Then…” rules are the
linguistic notions behind Fuzzy Logic. Parking a
vehicle in parallel requires the driver to learn
gradually over time from constant external stimuli
exposure and generalization. This process is a kind
of neural network wherein the mathematical
models are derived from the driver’s parallel
parking strategy.
Parallel parking problem is generally
developing a robust path planning wherein a
vehicle must approach a vacant area and park into
the area without difficulty. Many studies have been
proposed to solve this problem giving sufficient
paths consequent from path tracking techniques.
Many studies about automated parallel parking are
mainly motion planning wherein no collisions are
met between the paths from initial position to goal
position while satisfying the non holonomic
constraints. By integrating the use of Neuro-Fuzzy
System and the 5th order polynomial as reference
path this study will satisfy these non holonomic
constraints. This paper aims to develop an
automated parallel parking strategy for a Car-Like-
Mobile Robot (CLMR) using Neuro-Fuzzy Logic
Control (NFLC) design with the aid of proximity
sensors and accelerometer at 4 major parking
conditions: sandwiched between two obstacles at
level and inclined state (Scenarios 1 & 2 and
Scenarios 3 & 4), behind an obstacle (Scenarios 5
& 6) and in front of an obstacle (Scenarios 7 & 8)
coming from either right or left.
The architecture projected in this study is
an Adaptive Neuro-Fuzzy Inference System
(ANFIS) structure, which is essentially a fuzzy
inference system subjected into the framework of
adaptive neural network. Sensor based approach is
used for the parallel parking architecture, which is
performing the parallel parking maneuver by solely
depending on sonar data.
II. KINEMATIC EQUATIONS
Figure 1. Dynamics and Angles Involved in the Vehicle
2014 IEEE Region 10 Symposium
978-1-4799-2027-3/14/$31.00 ©2014 IEEE 640