19-03-2012, 12:23 PM
SAFETY GUARD FOR VEHICLES AND TRAFFIC MANAGEMENT USING FUZZY LOGIC
ABSTRACT:
Fuzzy logic has been introduced to deal with vague, imprecise and uncertain problems.Fuzzy logic can find applications in many aspects of real life that exhibit incomplete information, as where there is lack of information, However, the pervasive presence of uncertainty in sensing makes the choice of a suitable tool of reasoning and decision making, that can deal with incomplete information, vital to ensure a robust control system.This paper in the first half deals with the uncertainity and ambiguity in a general robot navigation in un-engineered environment. The later half deals with our design of Intelligent Guided Vehicle mainly concentrating on collision avoidance using Fuzzy Logic. A feature of the vehicle includes the movements like forward, left and right. We use ultrasonic sensor to measure the distance between obstacle and the vehicle. The distance is displayed in LCD fixed in the vehicle. The speed of the vehicle is displayed in the LCD. Whenever the vehicle finds a speed breaker so near it gives an alarm indication and also displays it in the LCD. The ultrasonic sensor is used to measure the speed of the vehicle and the IR sensor to find the speed breaker. The fuzzy logic is applied to control the speed of the vehicle. It helps to reduce the speed of the vehicle step by step. Collision prevention sensors are fixed on the vehicle, so that when the sensor detects an object in front of the vehicle, it automatically reduces the speed of the vehicle. Also our project includes dim-dip operation. It is useful during night traveling to indicate the opposite vehicle by dim-dip operation automatically. In this project a LDR is used for this operation. The vehicle has Zonal alarm, which ensures public safety in and around school and hospital zones. When the automobile is near hospital or school zone, LCD automatically displays the zone where it is traveling.
INTRODUCTION:
Navigation of a machine is the control of motion of that machine from a start point to an end point in a workspace following a path that is either a curve or a series of joined segments. Autonomous navigation systems are usually classified in the following categories according to the characteristics of the environment in which they have to move: 1.structured or known environment, 2.semi-structured or partially known environments, and 3.unstructured or unknown environments. Fuzzy logic provides the means to represent vague and fuzzy information, manipulate it, and to draw inferences from it. In ordinary mathematics, information is of a crisp kind. It belongs to a set or it does not. The choice of a yes-or-no answer is possible and usually applied, but information could be lost in such a choice, as the degree of belonging is not taken into consideration. A fuzzy model is the idea of a fuzzy set. the fuzzy set has a function that admits a degree of membership in the set from complete exclusion (0) to absolute inclusion (1). The value zero is used to symbolize complete non-membership, the value 1 is used to symbolize complete membership, and values in between are used to symbolize intermediate degrees of membership. A fuzzy concept is a linguistic variable used to define a fuzzy subset, as CLOSE or FAR for a range of obstacle10 11. A Fuzzy set comes as a generalization of conventional set theory. It is a superset of conventional (crisp) logic that has been extended to handle the concept of partial truth – truth-values between “completely true” and “completely false”; allowing intermediate values between crisp values
FUZZY LOGIC CONTROLLER:
The four principal components of the fuzzy decision-making systems are (see Fig. 1):
1. The fuzzification interface: determines input and output variables and maps them into linguistic variables that are to be displayed on a universe of discourse.
2. The knowledge base: is a part of expert systems that contains the domain knowledge. Membership functions and control rules are decided by the experts at this point, based on their knowledge of the system.
3. The decision-making logic: treats a fuzzy set as a fuzzy proposition. One fuzzy proposition can imply another, and two or more fuzzy propositions can be associated by a Boolean connectivity relation to infer a final fuzzy proposition.
4. The defuzzification interface converts the fuzzy output into a crisp (nonfuzzy) value.
DEFINE THE FUZZY SETS
The laser scans in a range of tens of meters. Each obstacle detected has a depth variable from the robot This depth or range data has a different membership in each of the three range subsets. The range universe of discourse is discretized into 8 parameters
or levels with 3 fuzzy sets, where parameters and membership functions are chosen heuristically .
The Membership function
for the set “range”
The laser scans from –90o to +90o. This scope is divided in six subsets: Left Negative, Medium Negative, Zero Negative,
Zero Positive, Medium Positive, and Large Positive; where each subset has a membership function. Fig.5 shows the
Distribution of the directions with respect to the six fuzzy concepts or subsets, where the range universe of discourse is
Discretized into 13 parameters or levels with 6 fuzzy sets, where parameters and membership functions are chosen
Heuristically.
DEFINE THE FUZZY RULES: Each rule admits two inputs and implies two outputs, as follows:
• If (range is Near And angle is Zero Positive) Then distance is Medium and angle of deviation is Zero Negative.
• If (range is near and angle is Zero Negative) Then distance is Medium and angle of deviation is Zero Positive.
• If (range is Medium and angle is Zero Positive) Then distance is near and angle of deviation is Zero Negative.
• If (range is Medium and angle is Zero Negative) Then distance is near and angle of deviation is Zero Positive.
DEFUZZIFICATION
The laser range finder upon detecting an obstacle, returns range and orientation information to the fuzzy logic. A “Get Membership” routine is applied iteratively to get different range and direction memberships. The specified fuzzy rules are applied afterwards. In a crisp system the intersection of two sets contains the elements that are common to both sets. This is equivalent to the common logical AND operation