A distributed fuzzy logic controller for an autonomous vehicle

2004 ◽  
Vol 21 (10) ◽  
pp. 499-516 ◽  
Author(s):  
Neil Eugene Hodge ◽  
Linda Zhixia Shi ◽  
Mohamed B. Trabia
Author(s):  
John R. Canning ◽  
Dean B. Edwards

Abstract This paper presents a method for embedding human expert knowledge into a fuzzy logic controller. The method was developed while designing a fuzzy logic control system for an autonomous vehicle that utilized sparse sensor data for terrain classification. We will discuss the design for the fuzzy logic terrain classification system and use it as an example for explaining the embedding method. In the example, a human expert classified terrain features from sensor data provided by a two-dimensional computer simulation. From the information derived from the expert, we developed both a classification system for the terrain features and a fuzzy logic rule base for the controller. The simulation, along with an optimization algorithm, was then used to train the fuzzy logic controller to match the human responses.


Author(s):  
J K Ong ◽  
K Bouazza-Marouf ◽  
D Kerr

This paper presents a fuzzy logic control for the navigation of a mobile robotic system in gas pipelines. The robotic system is designed for a local gas distribution pipeline network with 150–300mm diameter pipes; common pipe fittings in use are straight and bend sections, reducers and slope pipe sections. The navigation problem forms a part of the current development of a new modular and semi-autonomous vehicle system. The vehicle control and navigation technique is implemented using a two-mode controller consisting of a proportional-integral-derivative (PID) and fuzzy logic control. The PID controller is responsible for direct control of the actuators, while the fuzzy logic controller is used to evaluate as well as to define the sensor outputs such as speed, climbing angle and rate of climbing angle in order to perceive the different types of pipe environment and vehicle actions. Since the navigation problem involves a multivariable input-output (MIMO) system, a cascaded hierarchical fuzzy model configuration is used to reduce the dimensionality of the fuzzy model. The fuzzy navigation controller is thus an interlink fuzzy subsystem of the pipe environment recognition and action adjustment subsystems. Results of simulations and laboratory experiments are presented to demonstrate the ability of the control strategy. A brief description of the mobile robotic system used is presented as background.


Author(s):  
J K Ong ◽  
D Kerr ◽  
K Bouazza-Marouf

This paper presents a new solution for inspecting and repairing defects in live gas pipelines. The proposed approach is the development of a modular and semi-autonomous vehicle system. The robotic system has a drive mechanism, capable of navigating and adjusting its orientation in various configurations of pipelines. Other features of the system are cable-free communications, semi-autonomous motion control as well as integration of sensory devices. The robotic system is designed to traverse in 150–300 mm diameter pipes through straight and curved sections, junctions and reducers. The vehicle control and navigation technique is implemented using a two-mode controller consisting of a proportional-integral-derivative (PID) and fuzzy logic control. Unlike other available systems, the vehicle employs proprioceptive sensors to monitor its own states. The fuzzy logic controller is used to evaluate the sensor outputs such as speed, climbing angle and rate of change of climbing angle. This control technique allows the vehicle to drive and adapt in a partially observable gas pipe system. Laboratory experiment results are presented. The paper also describes a cable-free communication method for the system. A brief account of typical pipe environments and currently available inspection tools is presented as background information.


1999 ◽  
Author(s):  
Neil Eugene Hodge ◽  
Linda Zhixia Shi ◽  
Mohamed B. Trabia

Abstract Autonomous vehicles can be used in variety of applications such as hazardous environment or intelligent highway system. Fuzzy logic seems to be an appropriate choice for this area since it can deal with uncertainties. This paper proposes a fuzzy logic controller for the speed of an autonomous vehicle as it moves toward a target amid static and dynamic obstacles. The controller is divided into separate modules to mimic the way humans think while driving. One module speeds and slows the vehicle as it moves toward the target while another controls the speed in the neighborhood of obstacles. A third module controls the speed of the vehicle as it turns sharp corners. The paper also proposes a method for automatic tuning of the target throttle control module to stabilize the velocity of the vehicle as it approaches its target. The paper contains a simulation example to demonstrate the presented concepts.


2019 ◽  
Vol 3 (1) ◽  
pp. 186-192
Author(s):  
Yudi Wibawa

This paper aims to study for accurate sheet trim shower position for paper making process. An accurate position is required in an automation system. A mathematical model of DC motor is used to obtain a transfer function between shaft position and applied voltage. PID controller with Ziegler-Nichols and Hang-tuning rule and Fuzzy logic controller for controlling position accuracy are required. The result reference explains it that the FLC is better than other methods and performance characteristics also improve the control of DC motor.


Sign in / Sign up

Export Citation Format

Share Document