SELF DRIVING CAR

USING ARDUINO

GUIDED BY :- PROF. RUSHABH SHAH

PRESENTED BY :-
18MCA158 DIKPAL JHALA
18MCA164 RUJU SHAH
18MCA165 SIDDHI SHAH
 ABSTRACT

• OUR PROJECT IS AN AUTONOMOUS CAR WHICH DETECTS THE OBJECTS AND

MAKE PATH FOR ITSELF USING ARDUINO AND ULTRASONIC SENSOR .
• SELF DRIVING CAR OR AUTONOMOUS GUIDED VEHICLE IS A SELF-PILOTED
VEHICLE THAT DOES NOT REQUIRE AN OPERATOR TO NAVIGATE AND
ACCOMPLISH ITS TASKS.
• OBSTACLE DETECTION AND AVOIDANCE ARE ACHIEVED BY INCORPORATING A
ULTRASONIC SENSOR TO MEASURE THE DISTANCE BETWEEN THE VEHICLE
AND THE OBSTACLE, AND AVOIDANCE IS IMPLEMENTED BY THE MICRO-
CONTROLLER.
 INTRODUCTION

• THIS RESEARCH IS AIMING TO STUDY A POSSIBLE CONSTRUCTION OF A SELF

DRIVING TOY CAR PROVIDING IT WITH THE ABILITY TO AVOID OR RELEASE
ITSELF FROM ROAD OBSTACLES.
• THIS PROJECT AIMING TO DEFINE AND DEVELOP NEW APPROACHES TO MOVE
OBJECTS BY RAISING THE SELF AWARENESS OF THESE OBJECTS.
• TO PROVIDING A TOY CAR WITH THE ABILITY OF SENSING REAL WORLD, TO
REACHING THIS LEVEL OF COMMUNICATION A PHYSICAL SENSOR IS NEEDED
AND DIGITAL CONTROLLER BOARD AND DIFFERENT ELECTRIC MOTORS TO
EXCHANGE THE DIGITAL DATA INTO AN ACTUAL PHYSICAL RESPONSES.
 OBJECTIVES

• THIS RESEARCH OBJECTIVES IS THE POSSIBILITY TO USE A SIMPLE WORKING

PLATFORM TO CREATE A RESPONSIVE TOY CAR THAT CAN RECOGNIZE
OBSTACLES AND DECIDE A SUITABLE ACTION TO AVOID IT.

• COMBINE AN ELECTRONIC PLATFORM, A PHYSICAL STRUCTURE OF A TOY

CAR, ULTRASONIC SENSORS AND A SOFTWARE TO HAVE BENEFIT FROM ALL
OF THESE COMPONENTS INSTANTLY
 SCOPE OF PROJECT

• THE PROJECT CONTAIN THREE MAIN PARTS:

➢ CONTROLLING AGENT
➢ COMMUNICATION WITH PHYSICAL WORLD
➢ FORMING AN ACTION IN REAL WORLD
 CONTROLLING AGENT

• ARDUINO : IS AN OPEN SOURCE ELECTRONIC PLATFORM BASED ON EASY TO

USE HARDWARE AND SOFTWARE

• IT IS AN USER COMMUNITY THAT DESIGNS AND MANUFACTURES SINGLE-

BOARD MICROCONTROLLERS AND MICROCONTROLLER KITS FOR BUILDING
DIGITAL DEVICES
COMMUNICATION WITH PHYSICAL WORLD

• THE CAR IS EQUIPPED WITH A SENSOR THAT CAN PROVIDE INFORMATION

ABOUT PHYSICAL OBSTACLES.

• COMMUNICATION WITH PHYSICAL ENVIRONMENT USING DIFFERENT SENSORS

SUCH AS THE ULTRASONIC SENSORS
 FORMING AN ACTION IN REAL WORLD

• TRANSFORMING THE DIGITAL DATA IN TO PHYSICAL RESPONSES USING

DIFFERENT TYPE OF MOTORS.

• IN OUR PROJECT, WE USE DC MOTOR FOR OUR AUTONOMOUS TOY CAR.

 HARDWARE REQUIREMENT

• ARDUINO UNO
• ULTRASONIC SENSOR TO DETECT OBSTACLES
• DC MOTORS
• L293D CHIP
• JUMPER WIRES TO CONNECT INDIVIDUAL COMPONENTS
• CHASSIS, WHEELS, CASTOR WHEEL
 ARDUINO UNO

• ARDUINO UNO IS A MICROCONTROLLER BOARD BASED ON THE ATMEGA328P.

• IT HAS 14 DIGITAL INPUT/OUTPUT PINS (OF WHICH 6 CAN BE USED AS PWM
OUTPUTS), 6 ANALOG INPUTS, A 16 MHZ QUARTZ CRYSTAL, A USB
CONNECTION, A POWER JACK, AN ICSP HEADER AND A RESET BUTTON.
• IT CONTAINS EVERYTHING NEEDED TO SUPPORT THE MICROCONTROLLER;
SIMPLY CONNECT IT TO A COMPUTER WITH A USB CABLE OR POWER IT WITH
A AC-TO-DC ADAPTER OR BATTERY TO GET STARTED..
 ULTRASONIC SENSOR

• THE ULTRASONIC SENSOR IS USED FOR OBSTACLE DETECTION. ULTRASONIC

SENSOR TRANSMITS THE ULTRASONIC WAVES FROM ITS SENSOR HEAD AND
AGAIN RECEIVES THE ULTRASONIC WAVES REFLECTED FROM AN OBJECT.
• THERE ARE MANY APPLICATIONS USE ULTRASONIC SENSORS LIKE
INSTRUCTION ALARM SYSTEMS, AUTOMATIC DOOR OPENERS ETC. THE
ULTRASONIC SENSOR IS VERY COMPACT AND HAS A VERY HIGH
PERFORMANCE.
 MOTOR & L293D CHIP

• DC MOTORS USE PERMANENT MAGNETS OR ELECTROMAGNETIC WINDINGS TO

CONVERT ELECTRICAL ENERGY TO MECHANICAL ENERGY THAT PRODUCES HIGH
STARTING TORQUE AND POWER.
• TORQUE COMBINED WITH HIGH VOLTAGE DRIVES HEAVY LOADS WHEN THE MOTOR
IS STARTED. THESE MOTORS USE VOLTAGE TO CHANGE SPEEDS AND CAN BE USED
FOR PRECISE SPEEDS AS WELL AS POSITIONING. DC MOTORS ARE USED ON
CONVEYOR BELTS, ELEVATORS, CRANES, AND HOISTS.
• THIS DUAL BIDIRECTIONAL CHIP IS BASED ON THE VERY POPULAR L298 DUAL H-
BRIDGE MOTOR DRIVER IC. THIS MODULE WILL ALLOW YOU TO EASILY AND
INDEPENDENTLY CONTROL TWO MOTORS OF UP TO 2A EACH IN BOTH DIRECTIONS.
• IT IS IDEAL FOR ROBOTIC APPLICATIONS AND WELL SUITED FOR CONNECTION TO A
MICROCONTROLLER REQUIRING JUST A COUPLE OF CONTROL LINES PER MOTOR.
DC MOTOR L293D CHIP
 FOLLOWING CONCEPTS AND TOOLS ARE
USED IN LANE DETECTION:

• CANNY EGDE DETECTION

• HOUGH TRANSFORM.(FOR SHAPE DETECTION)

• GAUSSIAN BLURR.
 CANNY/SOBEL EGDE DETECTION:

• THE CANNY EDGE DETECTOR WAS DEVELOPED BY JOHN F. CANNY IN 1986.

ALSO KNOWN TO MANY AS THE OPTIMAL DETECTOR, CANNY ALGORITHM
AIMS TO SATISFY THREE MAIN CRITERIA:
• LOW ERROR RATE: MEANING A GOOD DETECTION OF ONLY EXISTENT EDGES.
• GOOD LOCALIZATION: THE DISTANCE BETWEEN EDGE PIXELS DETECTED AND
REAL EDGE PIXELS HAVE TO BE MINIMIZED.
• MINIMAL RESPONSE: ONLY ONE DETECTOR RESPONSE PER EDGE
 IMPLEMENTATION OF CANNY EDGE
DETECTION
• FILTER OUT ANY NOISE. THE GAUSSIAN FILTER IS USED FOR THIS PURPOSE.
• NON-MAXIMUM SUPPRESSION IS APPLIED. THIS REMOVES PIXELS THAT ARE NOT CONSIDERED
TO BE PART OF AN EDGE. HENCE, ONLY THIN LINES (CANDIDATE EDGES) WILL REMAIN.
• HYSTERESIS: THE FINAL STEP. CANNY DOES USE TWO THRESHOLDS (UPPER AND LOWER):
• IF A PIXEL GRADIENT IS HIGHER THAN THE UPPER THRESHOLD, THE PIXEL IS ACCEPTED AS AN
EDGE.
• IF A PIXEL GRADIENT VALUE IS BELOW THE LOWER THRESHOLD, THEN IT IS REJECTED.
• IF THE PIXEL GRADIENT IS BETWEEN THE TWO THRESHOLDS, THEN IT WILL BE ACCEPTED ONLY
IF IT IS CONNECTED TO A PIXEL THAT IS ABOVE THE UPPER THRESHOLD.
 HOUGH TRANSFORM:

• HOUGH TRANSFORM IS A FUNCTION AVAILABLE IN OPENCV WHICH HELPS IN

SHAPE DETECTION OF SOME STANDARD GEOMETRICAL SHAPES LIKE CIRCLE,
LINE, ELLIPSE. I USED HOUGH LINE TRANSFORM FOR LANE DETECTION,
THERE ARE TWO TYPES OF HOUGH LINE TRANSFORM:
• 1) HOUGH STANDARD TRANSFORM.
• 2) HOUGH PROBABLISTIC TRANSFORM.
 HOUGH STANDARD TRANSFORM:

• HOUGH TRANSFORM IS THE TECHNIQUE TO FIND OUT LINES BY IDENTIFYING

ALL POINTS ON THE LINE. THIS IS DONE BY REPRESENTING A LINE AS POINT.
AND POINTS ARE REPRESENTED AS LINES/SINUSOIDAL(DEPENDING ON
CARTESIAN / POLAR CO-ORDINATE SYSTEM). IF MULTIPLE LINES/SINUSOIDAL
PASS THROUGH THE POINT , WE CAN DEDUCE THAT THESE POINTS LIE ON
THE SAME LINE.
• 1) CARTESIAN COORDINATE SYSTEM: PARAMETERS: (M,B).
• 2) POLAR COORDINATE SYSTEM: PARAMETERS: (R, THETA).
• THE THREE PLOTS INTERSECT IN ONE SINGLE POINT (0.925.9.6) THESE
COORDINATES ARE THE PARAMETERS ( 0,R) OR THE LINE IN WHICH (X0,Y0),
(X1,Y1) AND (X2,Y2) LAY. IT MEANS THAT IN GENERAL, A LINE CAN BE DETECTED
BY FINDING THE NUMBER OF INTERSECTIONS BETWEEN CURVES.
• THE MORE CURVES INTERSECTING MEANS THAT THE LINE REPRESENTED BY THAT
INTERSECTION HAVE MORE POINTS. IN GENERAL, WE CAN DEFINE A THRESHOLD
OF THE MINIMUM NUMBER OF INTERSECTIONS NEEDED TO DETECT A LINE
 HOUGH PROBABLISTIC TRANSFORM:
• IT IS MUCH MORE EFFICIENT AND ACCURATE WAY TO DETECT LINES THEN
HOUGH TRANSFORM BECAUSE INSTEAD OF RETURNING LINES IN POLAR
COORDINATES IT DIRECTLY GIVES TWO CARTESIAN COORDINATES OF THE
DETECTED LINES. SO IT IS EASY TO INTERPRET THE DATA RETURNED BY THE
FUNCTION .
 ADVANTAGES OF HOUGH PROBABLISTIC
OVER HOUGH STANDARD :
• (ADVANTAGES CAN BE CLEARLY SEEN FROM ABOVE TWO SCREENSHOT OF
HOUGH STANDARD AND HOUGH PROBABILISTIC IMPLEMENTATION ON A
ROAD.)
• IN HOUGH PROBABILISTIC, THERE IS A PARAMETER: MINLINELENGTH, IT IS
USED TO SET THE MINIMUM LINE LENGTH. LINE SEGMENTS SHORTER THAN
THAT ARE REJECTED, THIS IS NOT PRESENT IN HOUGH STANDARD
TRANSFORM.
• ANOTHER PARAMETER PRESENT IN HOUGH PROBABILISTIC WHICH IS NOT IN
STANDARD TRANSFORM: MAXLINEGAP – MAXIMUM ALLOWED GAP BETWEEN
POINTS ON THE SAME LINE TO LINK THEM.
• THIRD AND MOST IMPORTANT ADVANTAGE IS THAT HOUGH PROBABILISTIC
DIRECTLY RETURNS CARTESIAN COORDINATES NOT POLAR.
 GAUSSIAN BLURR:

• IN IMAGE PROCESSING, A GAUSSIAN BLUR (ALSO KNOWN AS GAUSSIAN SMOOTHING) IS THE

RESULT OF BLURRING AN IMAGE BY A GAUSSIAN FUNCTION. IT IS A WIDELY USED EFFECT IN
GRAPHICS SOFTWARE, TYPICALLY TO REDUCE IMAGE NOISE AND REDUCE DETAIL. THE
VISUAL EFFECT OF THIS BLURRING TECHNIQUE IS A SMOOTH BLUR RESEMBLING THAT OF
VIEWING THE IMAGE THROUGH A TRANSLUCENT SCREEN, DISTINCTLY DIFFERENT FROM
THE BOKEH EFFECT PRODUCED BY AN OUT-OF-FOCUS LENS OR THE SHADOW OF AN OBJECT
UNDER USUAL ILLUMINATION. GAUSSIAN SMOOTHING IS ALSO USED AS A PRE-PROCESSING
STAGE IN COMPUTER VISION ALGORITHMS IN ORDER TO ENHANCE IMAGE STRUCTURES AT
DIFFERENT SCALES—SEE SCALE SPACE REPRESENTATION AND SCALE SPACE
IMPLEMENTATION. IT IS USED TO REMOVE NOISE FROM THE INPUT IMAGE.
FOR EACH FRAME, THE FIRST STEP IS TO
GRAYSCALE THE IMAGE
THEN A GAUSSIAN FILTER IS APPLIED
CANNY EDGE DETECTION IS USED ON THE
SMOOTHED IMAGE
THRESHOLDING IS USED TO FILTER OUT
IRRELEVANT PARTS OF THE IMAGE
HOUGH LINES ARE FOUND AND SEPARATED
INTO POSITIVE AND NEGATIVE SLOPES
SLOPE AVERAGES AND X INTERCEPT AVERAGES ARE FOUND FOR
POSITIVE AND NEGATIVE LINES, AND THE AVERAGE LANE LINE
FOR POSITIVE AND NEGATIVE ARE FOUND
THE LANE IS FILLED IN AND THE RESULT IS
WRITTEN TO THE OUTPUT VIDEO
CAR SNAPSHOT
C
 CONCLUSION
• THE HEART OF THE PROJECT IS THE ANALYZING SYSTEM THAT MAKES THE
PROPER ACTION FOR EACH SITUATION.

• THE SELF DRIVING TOY CAR PERFORMANCE WAS ACCEPTABLE WITH

ACCEPTABLE ERROR MARGIN.

• THE SIMPLE SYSTEM ALLOWED AN EASY INSTALLATION ON THE TOY CAR

BODY AND THERE WAS NO NEED FOR EXTERNAL STRUCTURE OR A
STATIONARY PROCESSING UNIT.
THANK YOU