Award Date

1-1-1994

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Mechanical Engineering

Number of Pages

82

Abstract

A controller is developed to guide a four-wheeled vehicle through an unknown environment. The vehicle is equipped with an ultrasonic sensor that can rotate to survey the neighboring environment. A new path planning algorithm is developed that reduces the computational time while avoiding obstacles. The vehicle uses a fuzzy-logic controller to determine the corresponding change in steering. While fuzzy-logic controllers exhibit robustness under varying operating conditions, it is difficult to design a good controller when observations about the system are scarce or when the system has large number of inputs and outputs. Due to this fact, the performance of the fuzzy-logic controller is improved using nonlinear programming techniques. The algorithm automatically generates the fuzzy rules and redefines the shape of the membership sets of input and output variables for an optimal performance of the controller. The effects of changing: the velocity of the vehicle, the range of the ultrasonic sensor, and the time step of the controller of the autonomous vehicle are discussed.

Keywords

Autonomous; Controller; Environment; Fuzzy; Logic; Operation; Unknown; Vehicle

Controlled Subject

Mechanical engineering; Systems science

File Format

pdf

File Size

2375.68 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

https://doi.org/10.25669/rnry-dlcd


Share

COinS