Seminar Report 2013 Autonomous Car: Dept. of ECE, T.K.M Institute of Technology, Kollam

Seminar Report 2013 Autonomous Car
CHAPTER 1
INTRODUCTION
The inventions of the integrated circuit and later, the microcomputer, were major factors in the development of electronic control in automobiles. The importance of the microcomputer cannot be overemphasized as it is the brain that controls many systems in todays cars. For e ample, in a cruise control system, the driver sets the desired speed and enables the system by pushing a button. ! microcomputer then monitors the actual speed of the vehicle using data from velocity sensors. The actual speed is compared to the desired speed and the controller adjusts the throttle as necessary. ! completely autonomous vehicle is one in which a computer performs all the tas"s that the human driver normally would. #ltimately, this would mean getting in a car, entering the destination into a computer, and enabling the system. From there, the car would ta"e over and drive to the destination with no human input. The car would be able to sense its environment and ma"e steering and speed changes as necessary. This scenario would re$uire all of the automotive technologies mentioned above% lane detection to aid in passing slower vehicles or e iting a highway& obstacle detection to locate other cars, pedestrians, animals, etc.& adaptive cruise control to maintain a safe speed& collision avoidance to avoid hitting obstacles in the road way& and lateral control to maintain the cars position on the roadway. 'n addition, sensors would be needed to alert the car to road or weather conditions to ensure safe traveling speeds. For e ample, the car would need to slow down in snowy or icy conditions. (e perform many tas"s while driving without even thin"ing about it. )ompletely automating the car is a challenging tas" and is a long way off. *owever, advances have been made in the individual systems. +oogles robotic car is a fully autonomous vehicle which is e$uipped with radar and ,'-!. and such can ta"e in much more information, process it much more $uic"ly and reliably, ma"e a correct decision about a comple situation, and then implement that decision far better than a human can. +oogle anticipates that the increased accuracy of its automated driving system could help reduce the number of traffic/related injuries and deaths Dept. of ECE, T.K.M Institute Of Technology, Kollam 1
The +oogle car system combines information gathered for +oogle 0treet 1iew with artificial intelligence software that combines input from video cameras inside the car, a ,'-!. sensor on top of the vehicle, radar sensors on the front of the vehicle and a position sensor attached to one of the rear wheels that helps locate the car2s position on the map. !s of 3454, +oogle has tested several vehicles e$uipped with the system, driving 564,444 miles 7384,444 "m9 without any human intervention, the only accident occurring when one of the cars was rear/ended while stopped at a red light. +oogle anticipates that the increased accuracy of its automated driving system could help reduce the number of traffic/related injuries and deaths, while using energy and space on roadways more efficiently.
Figure 5.5 +oogle )ar The combination of these technologies and other systems such as video based lane analysis, steering and bra"e actuation systems, and the programs necessary to control all of the components will become a fully autonomous system. The problem is winning the trust of the people to allow a computer to drive a vehicle for them, because of this, there must be research and testing done over and over again to assure a near fool proof final product. The product will not be accepted instantly, but over time as the systems become more widely used people will realize the benefits of it.
Dept. of ECE, T.K.M Institute Of Technology, Kollam
CHAPTER 2
BLOCK DIAGRAM
The bloc" diagram of +oogles driverless car is shown below. 't includes sensor section, processor section and drive by wire technology.
Figure 3.5 :loc" diagram of the system The main controller of the vehicle is the microprocessor section. There are two processors& one is for the general wor"ing and one for handling the sensory inputs which is real time. There are two coprocessors for handling the steering and the bra"e. !ccelerator is directly controlled by the general purpose processor. The sensory inputs include inputs from the lidar, radar, position estimator and street view images. ,idar creates a 8 - images platform for mounting the obstacles and map. The camera visuals are used for detecting the colour of the traffic signal based on which the vehicle moves on the road. The general purpose processor is constantly communicating with the engine control unit. Dept. of ECE, T.K.M Institute Of Technology, Kollam 3
CHAPTER 3
CONTROL UNIT
3.1 HARDWARE SENSORS 3.1.1 Radar .adar is an object/detection system which uses electromagnetic waves specifically radio waves / to determine the range, altitude, direction, or speed of both moving and fi ed objects such as aircraft, ships, spacecraft, guided missiles, motor vehicles, weather formations, and terrain.
Figure 8.5 ;!)<; 0.0 .adar The radar dish, or antenna, transmits pulses of radio waves or microwaves which bounce off any object in their path. The object returns a tiny part of the wave2s energy to a dish or antenna which is usually located at the same site as the transmitter. The modern uses of radar are highly diverse, including air traffic control, radar astronomy, air/defense systems, antimissile systems& nautical radars to locate landmar"s and other ships& aircraft anti collision systems& ocean/surveillance systems, outer/space surveillance and rendezvous systems& meteorological precipitation monitoring& altimetry and flight/control systems& guided/missile target/locating systems& and ground/penetrating radar for geological observations. *igh tech radar systems are associated with digital signal processing and are capable of e tracting objects from very high noise levels. ! radar system has a transmitter that emits radio waves called radar signals in Dept. of ECE, T.K.M Institute Of Technology, Kollam 4
predetermined directions. (hen these come into contact with an object they are usually reflected and=or scattered in many directions. .adar signals are reflected especially well by materials of considerable electrical conductivity/ especially by most metals, by seawater, by wet land, and by wetlands. 0ome of these ma"e the use of radar altimeters possible. The radar signals that are reflected bac" towards the transmitter are the desirable ones that ma"e radar wor". 'f the object is moving either closer or farther away, there is a slight change in the fre$uency of the radio waves, due to the -oppler effect. .adar receivers are usually, but not always, in the same location as the transmitter. !lthough the reflected radar signals captured by the receiving antenna are usually very wea", these signals can be strengthened by the electronic amplifiers that all radar sets contain. ;ore sophisticated methods of signal processing are also nearly always used in order to recover useful radar signals. The wea" absorption of radio waves by the medium through which it passes is what enables radar sets to detect objects at relatively/long ranges at which other electromagnetic wavelengths, such as visible light, infrared light, and ultraviolet light, are too strongly attenuated. 0uch things as fog, clouds, rain, falling snow, and sleet that bloc" visible light are usually transparent to radio waves. )ertain, specific radio fre$uencies that are absorbed or scattered by water vapor, raindrops, or atmospheric gases 7especially o ygen9 are avoided in designing radars e cept when detection of these is intended. Finally, radar relies on its own transmissions, rather than light from the 0un or the ;oon, or from electromagnetic waves emitted by the objects themselves, such as infrared wavelengths 7heat9. This process of directing artificial radio waves towards objects is called illumination, regardless of the fact that radio waves are completely invisible to the human eye or cameras. *igh tech radar systems are associated with digital signal processing and are capable of e tracting objects from very high noise levels *ere we use the ;! )<; 0.0 .adar .esistant to inclement weather and harsh environmental conditions, 36 +*z ultra wide band 7#(:9 radar sensors provide object detection and trac"ing. >ar"ing assistance can be provided by rear mounted sensors with 5.? m range that can detect small objects in front of large objects and measure direction of arrival. 0ensors with ability to scan out up to 84 m Dept. of ECE, T.K.M Institute Of Technology, Kollam 5
provide warning of imminent collision so airbags can be armed and seat restraints pretension. Figure shows the .!-!. waves in the system
Figure 8.3 .!-!. waves in autonomous cars 3.1.2 Lidar ,'-!. 7,ight -etection !nd .anging also ,!-!.9 is an optical remote sensing technology that can measure the distance to, or other properties of a target by illuminating the target with light, often using pulses from a laser. ,'-!. technology has application in geometrics, archaeology, geography, geology, geomorphology, seismology, forestry, remote sensing and atmospheric physics, as well as in airborne laser swath mapping 7!,0;9, laser altimetry and ,'-!. )ontour ;apping. The acronym ,!-!. 7,aser -etection and .anging9 is often used in military conte ts. The term @laser radar@ is sometimes used even though ,'-!. does not employ microwaves or radio waves and is not therefore in reality related to radar. ,'-!. uses ultraviolet, visible, or near infrared light to image objects and can be used with a wide range of targets, including non/metallic objects, roc"s, rain, chemical compounds, aerosols, clouds and even single molecules. ! narrow laser
beam can be used to map physical features with very high resolution. ,'-!. has been used e tensively for atmospheric research and meteorology.
Figure 8.8 ,idar used for 8- imaging -ownward/loo"ing ,'-!. instruments fitted to aircraft and satellites are used for surveying and mapping. ! recent e ample being the A!0! B perimental !dvanced .esearch ,idar. 'n addition ,'-!. has been identified by A!0! as a "ey technology for enabling autonomous precision safe landing of future robotic and crewed lunar landing vehicles. (avelengths in a range from about 54 micrometers to the #1 7ca.3C4 nm9 are used to suit the target. Typically light is reflected via bac"scattering. There are several major components to a ,'-!. system% 5. ,aser D E44F5444 nm lasers are most common for non/scientific applications. They are ine pensive but since they can be focused and easily absorbed by the eye the ma imum power is limited by the need to ma"e them eye/safe. Bye/safety is often a re$uirement for most applications .! common alternative 5CC4 nm lasers are eye/safe at much higher power levels since this wavelength is not focused by the eye, but the detector technology is less advanced and so these wavelengths are generally used at longer ranges and lower accuracies. They are also used for military applications as 5CC4 nm is not visible in night vision goggles unli"e the shorter 5444 nm infrared laser. !irborne topographic mapping lidars generally use 54E6 nm diode pumped G!+ lasers, while bathymetric systems generally use C83 nm fre$uency doubled diode pumped G!+ lasers because C83 nm penetrates water with much less attenuation than does 54E6nm Dept. of ECE, T.K.M Institute Of Technology, Kollam 7
3. 0canner and optics D *ow fast images can be developed is also affected by the speed at which it can be scanned into the system. There are several options to scan the azimuth and elevation, including dual oscillating plane mirrors, a combination with a polygon mirror, a dual a is scanner. <ptic choices affect the angular resolution and range that can be detected. ! hole mirror or a beam splitter are options to collect a return signal.
Figure 8.6 8/- map of car surroundings 8. >hoto detector and receiver electronics D two main photo detector technologies are used in lidars% solid state photo detectors, such as silicon avalanche photodiodes, or photomultipliers. The sensitivity of the receiver is another parameter that has to be balanced in a ,'-!. design. 6. >osition and navigation systems D ,'-!. sensors that are mounted on mobile platforms such as airplanes or satellites re$uire instrumentation to determine the absolute position and orientation of the sensor. 0uch devices generally include a +lobal >ositioning 0ystem receiver and an 'nertial ;easurement #nit 7';#9.8imaging can be achieved using both scanning and non/scanning systems. @8- gated
viewing laser radar@ is a non/scanning laser ranging system that applies a pulsed laser and a fast gated camera. 3.1.3 Global Po i!io"i"# S$ !%& The +lobal >ositioning 0ystem 7+>09 is a space/based global navigation satellite 0ystem 7+A009 that provides location and time information in all weather, anywhere on or near the Barth, where there is an unobstructed line of sight to four or more +>0 satellites.+>0 receiver calculates its position by precisely timing the signals sent by +>0 satellites high above the Barth.
Figure 8.C +oogle ;ap Bach satellite continually transmits messages that include The time the message was transmitted >recise orbital information 7the ephemeris9 The general system health and rough orbits of all +>0 satellites The receiver uses the messages it receives to determine the transit time of each message and computes the distance to each satellite. These distances along with the satellites2 locations are used with the possible aid of trilateration, depending on which Dept. of ECE, T.K.M Institute Of Technology, Kollam 9
algorithm is used, to compute the position of the receiver. This position is then displayed, perhaps with a moving map display or latitude and longitude& elevation information may be included. ;any +>0 units show derived information such as direction and speed, calculated from position changes. Three satellites might seem enough to solve for position since space has three dimensions and a position near the Barth2s surface can be assumed. *owever, even a very small cloc" error multiplied by the very large speed of light D the speed at which satellite signals propagate results in a large positional error. Therefore receivers use four or more satellites to solve for the receiver2s location and time. The very accurately computed time is effectively hidden by most +>0 applications, which use only the location. ! few specialized +>0 applications do however use the time& these include time transfer, traffic signal timing, and synchronization of cell phone base stations. 3.1.' Po i!io" %" or ! position sensor is any device that permits position measurement *ere we use a rotator encoder also called a shaft encoder, is an electro/mechanical device that converts the angular position or motion of a shaft or a le to an analog or digital code. The output of incremental encoders provides information about the motion of the shaft which is typically further processed elsewhere into information such as speed, distance, .>; and position. The output of absolute encoders indicates the current position of the shaft, ma"ing them angle transducers. .otary encoders are used in many applications that re$uire precise shaft unlimited rotationDincluding industrial controls, robotics, special purpose photographic lenses, computer input devices 7such as opto mechanical mice and trac"balls9, and rotating radar platforms. 3.1. ( Ca&%ra +oogle has used three types of car/mounted cameras in the past to ta"e 0treet 1iew photographs. +enerations 5F8 were used to ta"e photographs in the #nited 0tates. The first generation was $uic"ly superseded and images were replaced with images ta"en with 3nd and 8rd generation cameras. 0econd generation cameras were used to ta"e photographs in !ustralia.
10
Figure 8.E 0treet 1iew camera system. The system is a rosette 7.9 of 5C small, outward/loo"ing cameras using C megapi el );<0 image sensors and custom, low/flare, controlled/distortion lenses. The shadows caused by the 5st, 3nd and 6th generation cameras are occasionally viewable in images ta"en in mornings and evenings. The new 6th generation cameras *- will be used to completely replace all images ta"en with earlier generation cameras. Thus the total sensor components can be e plained using the below figure assembled on the car. !ll the components are already e plained.
11
Figure 8.H )omponents of +oogle )ar
3.2 LOGIC PROCESSING UNIT 3.2.1 Goo#l% S!r%%! )i%* +oogle 0treet 1iew is a technology featured in +oogle ;aps and +oogle Barth that provides panoramic views from various positions along many streets in the world. 't was launched on ;ay 3C, 344H, originally only in several cities in the #nited 0tates, and has since gradually e panded to include more cities and rural areas worldwide. +oogle 0treet 1iew displays images ta"en from a fleet of specially adapted cars. !reas not accessible by car, li"e pedestrian areas, narrow streets, alleys and s"i resorts, are sometimes covered by +oogle Tri"es 7tricycles9 or a snowmobile. <n each of these vehicles there are nine directional cameras for 8E4I views at a height of about ?.3 feet, or 3.C meters, +>0 units for positioning and three laser range scanners for the measuring of up to C4 meters 5?4I in the front of the vehicle. There are also 8+=+0;=(i/Fi antennas for scanning 8+=+0; and (i/Fi hotspots. .ecently, 2high $uality2 images are based on open source hardware cameras from Blphel. Dept. of ECE, T.K.M Institute Of Technology, Kollam 12
Figure 8.? 0treet 1iew (here available, street view images appear after zooming in beyond the highest zooming level in maps and satellite images, and also by dragging a @pegman@ icon onto a location on a map. #sing the "eyboard or mouse the horizontal and vertical viewing direction and the zoom level can be selected. ! solid or bro"en line in the photo shows the appro imate path followed by the camera car, and arrows lin" to the ne t photo in each direction. !t junctions and crossings of camera car routes, more arrows are shown. 3.2.2 Ar!i+i,ial i"!%lli#%",% o+!*ar% !rtificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. !' te tboo"s define the field as @the study and design of intelligent agents where an intelligent agent is a system that perceives its environment and ta"es actions that ma imize its chances of success. John ;c)arthy, who coined the term in 5KCE, defines it as @the science and engineering of ma"ing intelligent machines@. *ere the details about the software are a trade secret of +oogle. The hardware components are placed in the vehicle boot and is shown below.
13
Figure 8.K *ardware assembly of the system 3.3 PROCESSOR UNIT 3.3.1 -%o" Pro,% or Leon >rocessor is a multi/core enterprise processors built on 83/nanometer process technology .'t has up to ? e ecution cores. Bach core supports two threads 7'ntel *yper/Threading9.The main features of Leon processor are% 6E/bit physical addressing and 6?/bit virtual addressing ! 83/M: instruction and 83/M: data first/level cache 7,59 for each core ! 3CE/M: shared instruction=data mid/level 7,39 cache for each core
(e need two processor here for handling real time sensor values and for general wor"ing. 3.3.1 Cor!%. Co/ro,% or Two separate )orte /!K processors are used for 0teering bra"e The !.; )orte /!K ;>)ore is a 83/bit multicore processor providing up to 6 cache/coherent )orte /!K cores, each implementing the !.; vH instruction set architecture. They are high performance !.; processor with 5/6 cores version .'t wor" on !L' high/speed !dvanced ;icroprocessor :us architecture. 'ts main feature is the increased pea" performance for most demanding applications CHAPTER ' Dept. of ECE, T.K.M Institute Of Technology, Kollam 14
ROBOTIC CAR DESIGN

'.1 MULTICORE HETROGENOUS COMPUTING ,ab 1'B( applications on two *> dual $uad/core servers performed sensor data and image processing and ran decision/ma"ing and planning modules. )ompact .'< managed the lower level vehicle interface. !n A' touch panel in the dashboard helped switch between autonomous and manual operation modes.
Figure 6.5 .obotic car design *eterogeneous computing systems refer to electronic systems that use a variety of different types of computational units. ! computational unit could be a general/purpose processor 7+>>9, a special/purpose processor 7i.e. digital signal processor 7-0>9 or graphics processing unit 7+>#99, a co/processor, or custom acceleration logic 7application/specific integrated circuit 7!0')9 or field/ programmable gate array 7F>+!99. 'n general, a heterogeneous computing platform consists of processors with different instruction set architectures 7'0!s9.
15
! multi/core processor is a single computing component with two or more independent actual processors 7called @cores@9, which are the units that read and e ecute program instructions. The data in the instruction tells the processor what to do. The instructions are very basic things li"e reading data from memory or sending data to the user display, but they are processed so rapidly that human perception e periences the results as the smooth operation of a program. ;anufacturers typically integrate the cores onto a single integrated circuit die 7"nown as a chip multiprocessor or );>9, or onto multiple dies in a single chip pac"age '.2 SENSOR DATA AC0UISITION 0ensor data ac$uisition and processing ,ab 1'B( applications running on multicore servers with ,inu and (indows <0s processed and analyzed data from three ':B< !,!0)! multi planar ,'-!.s, four 0')M ,;0 ,'-!.s, two 'BBB 58K6 cameras, and one Aovatel +>0='A0. Bthernet cables acted as the interface for all sensors. sensor data ac$uisition means gathering of the data that the sensors are providing which collected from the current environment, then the collected data is processed here. '.3 1AUS INTEROPERABLE COMMUNICATION Joint !rchitecture for #nmanned 0ystems 7J!#09, formerly "nown as Joint !rchitecture for #nmanned +round 0ystems 7J!#+09, was originally an initiative started in 5KK? by the #nited 0tates -epartment of -efense to develop an open architecture for the domain of unmanned systems. ,ab 1'B( helped develop and deploy a set of tools for J!#0, an autonomous ground vehicle standard for passing messages and status information among various vehicle subsystems. This 0!B !0/6 J!#0 interoperable architecture was designed for use in other autonomous applications as well. '.' DRI)E B2 WIRE S2STEM -rive/by/wire, technology in the automotive industry replaces the traditional mechanical control systems with electronic control systems using electromechanical actuators and human machine interfaces such as pedal and steering feel emulators. *ence, the traditional components such as the steering column, intermediate shafts, pumps, hoses, belts, coolers and vacuum servos and master cylinders are eliminated from the vehicle.
16
CHAPTER(
ALGORITHM
0tart simulation
'nitialize variables
-etermine cars position on the path
)alculate lateral deviation and heading angle
-etermine velocity and steering inputs
#pdate car position
Bnd
0how plots
Bnd simulation
Figure C.5 !lgorithm of car wor"ing (.1. INTERACTI)E ALGORITHM 'nteractive algorithms for path following involve direct communication with e ternal sources such as receiving navigation data from the leader or consulting +>0 coordinates. The Follow/the/>ast algorithm is one such e ample& it involves receiving
17
and interpreting position data, orientation data, and steering angle data from a leader vehicle. The objective is to mimic these three navigational properties in order to accurately follow the path set by the leader. !s orientation and steering angle are associated with +>0 positional data, the following vehicle can update its navigational state to match that of the leader vehicle at the appropriate moment in time. <ne developed algorithm is best described as a placing a trail of breadcrumbs based on the leading vehicle2s position. ! cubic spline fit is applied to the generated breadcrumbs to establish a smooth path by which to travel. This developed algorithm was tested and showed centimeter level precision in following a desired path.
18
CHAPTER 3
DRI)E B2 WIRE TECHNOLOG2

The wor"ing of the system can be e plained by using the integration of drive need to control only three driving parts. 0TBB.'A+ :.!MB T*.<TT,B by wire technology and processors using the artificial intelligence and the algorithm. (e
3.1 DRI)E B2 WIRE TECHNOLOG2 -rive/by/wire, -b(, by/wire, or /by/wire technology in the automotive industry replaces the traditional mechanical control systems with electronic control systems using electromechanical actuators and human/machine interfaces such as pedal and steering feel emulators. *ence, the traditional components such as the steering column, intermediate shafts, pumps, hoses, belts, coolers and vacuum servos and master cylinders are eliminated from the vehicle. B amples include electronic throttle control and bra"e/by/wire. 0afety can be improved by providing computer controlled intervention of vehicle controls with systems such as Blectronic 0tability )ontrol 7B0)9, adaptive cruise control and ,ane !ssist 0ystems. Brgonomics can be improved by the amount of force and range of movement re$uired by the driver and by greater fle ibility in the location of controls. This fle ibility also significantly e pands the number of options for the vehicle2s design. The cost of -b( systems is often greater than conventional systems. The e tra costs stem from greater comple ity, development costs and the redundant elements needed to ma"e the system safe. Failures in the control system could theoretically cause a runaway vehicle, although this is no different from the throttle return spring snapping on a traditional mechanical throttle vehicle. !nother disadvantage is that manufacturers often reduce throttle sensitivity in the low/mid Dept. of ECE, T.K.M Institute Of Technology, Kollam 19
throttle range to ma"e the car easier or safer to control / or to protect the drive train 7gearbo , clutch, etc.9 from driver abuse. The normal drive by wire technology and associated hardware are shown in the figure.
Figure E.5 -rive by wire technology 3.2 STEER B2 WIRE 0teer by wire can be basically e plained with the help of electronic power steering technology. !lmost all modern vehicles are based on electronic power steering 7B>09. B>0 systems have variable power assist, which provides more assistance as the speed of a vehicle decreases and less assistance at higher speeds. They do not re$uire any significant power to operate when no steering assistance is re$uired. For this reason, they are more energy efficient than hydraulic systems.
20
Figure E.3 Blectronic power steering The B>0 electronic control unit 7B)#9 calculates the assisting power needed based on the tor$ue being applied to the steering wheel by the driver, the steering wheel position and the vehicles speed. The B>0 motor rotates a steering gear with an applied force that reduces the tor$ue re$uired from the driver. The steering angle and tor$ue is obtained from the steering and the motor drives it freely for the driver with much easiness. The motor is controlled by the engine control unit by chec"ing the vehicle speed. There are four forms of B>0, based on the position of the assist motor. They are the column assist type 7)/B>09, the pinion assist type 7>/B>09, the direct drive type 7-/B>09 and the rac" assist type 7./B>09. The -/B>0 system has low inertia and friction because the steering gear and assist unit are a single unit. The ./B>0 type has the assist unit connected to the steering gear. ./B>0 systems can be used on mid/ to full/sized vehicles due to their very relatively low inertia from high reduction gear ratios. . These systems can be tuned by simply modifying the software controlling the B)#. This provides a uni$ue and cost effective opportunity to adjust the steering @feel@ to suit the automotive model class. !dditional advantages of B>0 are its ability
21
to compensate for one/sided forces such as a flat tire. 't is also capable of steering in emergency maneuvers in conjunction with the electronic stability control. 'n driverless car the steering angle and the steering tor$ue are calculated based on the algorithm and the data is fed on the B)#. 0o the driver need not to adjust the vehicle, the B)# controlled motor will rotate the steering. 4.2 BRAKE B2 WIRE :ra"e/by/wire refers to the technology in which mechanical and hydraulic components of traditional bra"ing systems are replaced by electronic sensors and actuators to carry out the function of bra"ing in a vehicle. :ra"e/by/wire is a combination of electronic control systems coupled with a set of electromechanical actuators and a human/machine interface, which is in this case, the bra"e pedal. The use of bra"e/by/wire systems enumerate many benefits such as weight reduction and space saving, lower operating noises and vibrations, and $uic"er reaction time due to the absence of mechanical lin"ages, which would result in shorter stopping distances. *owever for successful application on an e tensive basis, the wrin"les in the system2s wor"ing need to be ironed out to devise a fail/safe version with a clear indication of its distinctive advantages over conventional bra"ing systems, to warm vehicle manufacturers and consumers ali"e to the idea of its ubi$uitous implementation in vehicles. -ue to the safety critical nature of bra"e/by/wire systems, incorporating a degree of fault tolerance is vital. The most commonly suggested solution is a redundant or bac"/up bra"e system, such as a conventional hydraulic system, that would be brought into activation in the event that the primary system suffers a failure.
22
Figure E.8 :ra"e by wire technology The bra"e pedal sensor input is calculated using the radar and lidar using the algorithm .'t is dependent on the distance to the object and bra"ing emergency. The sensory input ma"es the driver free from applying bra"es. 3.3 THROTTLE B2 WIRE Blectronic throttle control 7BT)9 is an automobile technology which connects the accelerator pedal to the throttle, replacing a mechanical lin"age. ;ost automobiles already use a throttle position sensor 7T>09 to provide input to traction control, antiloc" bra"es, fuel injection, and other systems, but use a bowden cable to directly connect the pedal with the throttle. !n BT)/e$uipped vehicle has no such cable. 'nstead, the electronic control unit 7B)#9 determines the re$uired throttle position by calculations from data measured by other sensors such as an accelerator pedal position Dept. of ECE, T.K.M Institute Of Technology, Kollam 23
sensor, engine speed sensor, vehicle speed sensor etc. The electric motor within the BT) is then driven to the re$uired position via a closed/loop control algorithm within the B)#. The benefits of BT) are largely unnoticed by most drivers because the aim is to ma"e the vehicle power/train characteristics seamlessly consistent irrespective of prevailing conditions, such as engine temperature, altitude, accessory loads etc. The BT) is also wor"ing 2behind the scenes2 to dramatically improve the ease with which the driver can e ecute gear changes and deal with the dramatic tor$ue changes associated with rapid accelerations and decelerations. BT) facilitates the integration of features such as cruise control, traction control, stability control, and precrash systems and others that re$uire tor$ue management, since the throttle can be moved irrespective of the position of the driver2s accelerator pedal. BT) provides some benefit in areas such as air/fuel ratio control, e haust emissions and fuel consumption reduction, and also wor"s in concert with other technologies such as gasoline direct injection.
CHAPTER 4
ONGOING RESEARCHES IN THE 5IELD

!s of 3454, +oogle has tested several vehicles e$uipped with the system, driving 5,444miles 75,E44 "m9 without any human intervention, in addition to 564,444 miles 7384,444 "m9 with occasional human intervention, the only accident occurring when a car crashed into the rear end of a test vehicle while stopped at a red light. The project team has e$uipped a test fleet of seven vehicles, consisting of si Dept. of ECE, T.K.M Institute Of Technology, Kollam 24
Toyota >rius and an !udi TT, each accompanied in the driver2s seat by one of a dozen drivers with unblemished driving records and in the passenger seat by one of +oogle2s engineers. The car has traversed 0an Francisco2s ,ombard 0treet, famed for its steep hairpin turns and through city traffic. The vehicles have driven over the +olden +ate :ridge and on the >acific )oast *ighway, and have circled ,a"e Tahoe. The system drives at the speed limit it has stored on its maps and maintains its distance from other vehicles using its system of sensors. The system provides an override that allows a human driver to ta"e control of the car by stepping on the bra"e or turning the wheel, similar to cruise control systems already in cars. ;any companies such as +eneral ;otors, 1ol"swagen, !udi, :;(, 1olvo, have begun testing driverless car systems. +eneral ;otors has stated that they will begin testing driverless cars by 345C, and they could be on the road by 345?. 1olvo has begun to develop an almost autonomous road train system for highways which could be integrated in cars by 3434. +oogle has lobbied for two bills which, in June 3455, made Aevada the first state where driverless vehicles can be legally operated on public roads. The first bill is an amendment to an electric vehicle bill that provides for the licensing and testing of autonomous vehicles. The second bill provides an e emption from the ban on distracted driving to permit occupants to send te t messages while sitting behind the wheel.. 'n 344E the #nited Mingdom government2s 2Foresight2 thin"/tan" revealed a report which predicts a .F'-/ tagged driverless cars on #M2s roads by 34CE, and the .oyal !cademy of Bngineering claims that driverless truc"s could be on :ritain2s motorways by 345K.
CHAPTER 6
APPLICATIONS
The various applications of the technology are 1. I"!%lli#%"! !ra" /or!i"# 'ntelligent transport systems vary in technologies applied, from basic management systems such as car navigation& traffic signal control systems& container management systems& variable message signs& automatic number plate recognition or Dept. of ECE, T.K.M Institute Of Technology, Kollam 25
speed cameras to monitor applications, such as security ))T1 systems& and to more advanced applications that integrate live data and feedbac" from a number of other sources, such as par"ing guidance and information systems& weather information& bridge deicing systems& and the li"e. !dditionally, predictive techni$ues are being developed to allow advanced modeling and comparison with historical baseline data this technology will be a revolutionary step in intelligent transportation. 2. Mili!ar$ a//li,a!io" !utomated navigation system with real time decision ma"ing capability of the system ma"es it more applicable in war fields and other military applications. 3. Tra" /or!a!io" i" 7a8ardo9 /la,% The complete real time decision ma"ing capability and sensor guided navigation will leads to replace the human drivers in hazardous place transportation. '. S7i//i"# !utonomous vehicles will have a huge impact on the land shipping industry. <ne way to transport goods on land is by freight truc"s. There are thousands of freight truc"s on the road everyday driving for multiple days to reach their destination. !ll of these truc"s are driven by a paid employee of a truc"ing company. 'f the truc"s were able to drive on their own, a person to move the vehicle from one point to another is no longer needed. The truc" is also able to drive to their destination without having to stop to sleep, eat, or anything besides more fuel. !ll that is necessary is someone to load the vehicle and someone to unload the vehicle. This would save truc"ing companies a very large amount of money, but it would also put thousands of people out of jobs. These people would have to find and learn a new profession as driving a freight truc" is a full time job with little time spent at home to learn how to do another profession. This is potentially life ruining for many employees in this industry (. Ta.i %r:i,% !nother business that would be strongly affected is ta i services. 't is based solely on driving someone around who does not have a car or does not want to drive. Then an employee is dispatched to go and pic" up the person and bring them to their destination. This type of service could lower the number of vehicles on the road because not everyone would have to own a car, people could call to re$uest an autonomous car to bring them around. Ta is also drive around cities and wait in busy areas for people to re$uest a cab. ! ta i service comprised completely of autonomous Dept. of ECE, T.K.M Institute Of Technology, Kollam 26
vehicles could be started. ! person can call in and re$uest to be pic"ed up and then be brought to their destination for a fee. There could be autonomous ta is waiting in designated areas for people to come and use them. ;any ta i drivers need the job because they are unable to perform other jobs for various reasons. The need for a human in the service goes away almost completely. This is another e ample of a large amount of people being removed from their jobs because of autonomous vehicles being able to perform the tas" without the need of an e tra person. 3. P9bli, !ra" /or!a!io" 1arious forms of public transportation are controlled by a human operator. (hether it is on a bus, in a train, subway, streetcar, or shuttle, there is a person sitting in the drivers seat and they are controlling what the vehicle is doing. For trains and other rail/based transportation, it is a simpler process more involved with accelerating and decelerating the train from and into stops with no concern over "eeping in a lane. *owever, on a bus or shuttle, a person must follow rules, watch the actions of other drivers and pedestrians, "eep the bus in lane, and ma"e sure they stop at every bus station. These are many tas"s that one person must be able to handle and react to and control at the same time. 'n the early stages of implementation, it would most li"ely "eep the driver behind the wheel as a safeguard in case there is a problem with the system. The driver would also be needed in the beginning in order for the general public to trust it at first. !s the life of the autonomous vehicle systems progresses, bus drivers would no longer be needed as the system would be able to perform all of the re$uired tas"s. 't is a simple job of following a specific route and stopping at designated points. The problems would arise from actions of other vehicles in the area. The most ideal situation is when the autonomous vehicle systems have matured to the point that nearly every vehicle on the road is autonomously driven. CHAPTER ;
MERITS AND DEMERITS

1<.1 MERITS 0afety 0afety issues have the most serious impact on daily life out of all the transportation problems. Traffic accidents have colossal negative effects on economy. Dept. of ECE, T.K.M Institute Of Technology, Kollam 27
Traveling by car is currently the most deadly form of transportation, with over a million deaths annually worldwide. For this reason, the majority of the research projects in the transportation sector concentrate on developing safety systems. 'mplementation of autonomous vehicles can greatly reduce the number of crashes, since K4 percent of the traffic accidents are caused by human error. 'ntelligent safety systems that are currently in use have already proven their success in helping drivers avoid accidents. !ccording to B#.<0T!T data, the number of road fatalities in the B# has been reduced from CE,43H to3?,?6K people per year between the years of 5KK5 and 3454.This data indicates a reduction of about 84 percent, which reflects the better safety performance of recent vehicles when compared to previous vehicle generations. 'mpacts on Traffic (ith the introduction of a fully autonomous vehicle, traffic flow would drastically change. Traffic is currently a nuisance to drivers all over the world. 'n the early stages of implementation to the highway system there would be a combination of autonomously driven vehicles and human controlled vehicles. This could cause some confusion and problems concerning the reaction of motorists to the driverless vehicles and how well the autonomous vehicles can integrate into traffic flow. The autonomous vehicles would be following all traffic laws while human drivers have the choice to brea" the law. !s time progresses and the autonomous car becomes a more commonly used vehicle on the road, traffic would become far less congested. )ars would be able to seamlessly merge into moving traffic and then e it the highway just as easily. (ith the reduction of traffic, there is a chance that there could be economic improvements. !lso, with less stop and go traffic, average fuel economy would be improved. 1ehicles are also following each other consistently which would help with fuel usage as well. Fuel economy !utonomous vehicles will eliminate ineffective speeding up and bra"ing, operating at an optimum performance level in order to achieve best possible fuel efficiency. Bven if the fuel efficiency achieved by the autonomous vehicles were 5 percent better, this would result in billions of dollars of savings in the #0 alone. 't is possible to obtain superior fuel efficiency as a result of the implementation of Dept. of ECE, T.K.M Institute Of Technology, Kollam 28
autonomous safety systems. Total savings that can be achieved by the increased fuel efficiency can be calculated by ma"ing some assumptions such as% o 54N as a result of more efficient driving. o CN as a result of cars being 844 pounds lighter on average. o 54N as a result of more efficient traffic flow. !ccording to the assumptions made above, the implementation autonomous vehicles will result into fuel savings of 3C percent, which is rough estimate Time )osts The phrase Otime is money is true for most situations in modern life and the monetary value of time is increasing every day. #sing automated cars could save considerable amount of time in a persons life, especially if the person resides in a busy city. Bven if the time savings were not considered as having monetary value, having more time for leisure activities would raise our life standards. ,owering the amount of time lost will also enable people to be on time and more dynamic, resulting in a significant improvement in wor" efficiency. <ne of the biggest advantages of this technology will be the elimination of traffic problems in cities, which are at the top of the most frustrating problems list for most people. :y enabling a smoother traffic flow, the new system will be saving a lot of time which can be used for wor" or leisure.
Figure K.5 Features of autonomous car
29
;.2 DEMERITS The e$uipments and technologies used are costly the main e$uipments used
in this technology are radar, lidar, position sensor, gps module, ;ulticore heterogeneous processor, J!#0 interoperable communication systems, high resolution cameras are very costly now. )omple artificial intelligence software the brain of the robotic car is its intelligent real time decision ma"ing software the design and implementation of this part of the system is much more complicated. >resent road conditions may vary and which will affect the decisions made by
the software since our system is mainly based on pure artificial intelligence, the non ideal conditions and decisions made by other human drivers may vary. This may affect the ideal operation of the robotic car. >rofessional drivers will be jobless
CHAPTER 1< 5UTURE SCOPE The transition to an automated transportation structure will greatly prevent many problems caused by the traffic. 'mplementation of autonomous cars will allow the vehicles to be able to use the roads more efficiently, thus saving space and time. (ith having automated cars, narrow lanes will no longer be a problem and most traffic problems will be avoided to a great e tent by the help of this new technology. .esearch indicates that the traffic patterns will be more predictable and less problematic with the integration of autonomous cars. 0mooth traffic flow is at the top Dept. of ECE, T.K.M Institute Of Technology, Kollam 30
of the wish list for countless transportation officials. )ar manufacturers are already using various driver assist systems in their high/end models and this trend is becoming more and more common. !s a result of this trend, the early co/ pilot systems are e pected to gradually evolve to auto/pilots. !ll developments show that one day the intelligent vehicles will be a part of our daily lives, but it is hard to predict when. The most important factor is whether the public sector will be proactive in ta"ing advantage of this capability or not. The >ublic 0ector will determine if the benefits will come sooner rather than later. 0ince these assist systems are very similar with the systems that are used in autonomous car prototypes, they are regarded as the transition elements on the way to the implementation fully autonomous vehicles.
CHAPTER 11
CONCLUSION
)urrently, there are many different technologies available that can assist in creating autonomous vehicle systems. 'tems such as +>0, automated cruise control, and lane "eeping assistance are available to consumers on some lu ury vehicles. The combination of these technologies and other systems such as video based lane analysis, steering and bra"e actuation systems, and the programs necessary to control all of the components will become a fully autonomous system. The problem is winning the trust of the people to allow a computer to drive a vehicle for them, Dept. of ECE, T.K.M Institute Of Technology, Kollam 31
because of this, there must be research and testing done over and over again to assure a near fool proof final product. The product will not be accepted instantly, but over time as the systems become more widely used people will realize the benefits of it. The implementation of autonomous vehicles will bring up the problem of replacing humans with computers that can do the wor" for them. There will not be an instant change in society, but it will become more apparent over time as they are integrated into society.
RE5ERENCES
5.Thorsten ,uettel, ;ichael *immelsbach, and *ans/Joachim (uensche, !utonomous +round 1ehicles/)oncepts and a >ath to the Future, Vol. 100, May 13th,Proceedings of the IEEE,2012 3. 0. Thrun, (. :urgard, and -. Fo , Probabilistic Robotics (Intelligent Robotics and A tono!o s Agents", 3445 . Dept. of ECE, T.K.M Institute Of Technology, Kollam 32
8. Ailotpal )ha"raborty, .aghvendra 0ingh >atel, 'ntelligent !gents and !utonomous )ars % ! )ase 0tudy, International #o rnal of Engineering Research $ %echnology (I#ER%", I&&'( 22)*+01*1, Vol. 2 Iss e 1, #an ary+ 2013 6. -ragomir !nguelov, )arole -ulong, -aniel Filip, )hristian Frueh, 0tPphane ,afon +oogle 0treet 1iew% )apturing the (orld at 0treet ,evel, International #o rnal of Engineering Research $ %echnology (I#ER%",Vol.,3, Iss e(- Page(s"(32 . 3*.2011 C. Julien ;oras, 1Qeroni$ue )herfaoui, >hillipe :onnifait ! lidar >erception 0cheme for 'ntelligent 1ehicle Aavigation 11th International /onference on /ontrol A to!ation Robotics $ Vision (I/AR/V", Pages: 1*00 . 1*1,, 2010 , E. !. Frome , @,arge/0cale >rivacy >rotection in +oogle 0treet 1iew@, Proc. 12th IEEE Int12l /onf. /o!3 ter Vision (I//V 00", 344K H.'sermann, .olf,Fault/tolerant drive/by/wire systems,vol 33 , International #o rnal of Engineering Research $ %echnology (I#ER%", , Iss e( 4 ,3ages -, . *1,5ol- ,2011
33

Seminar Report 2013 Autonomous Car: Dept. of ECE, T.K.M Institute of Technology, Kollam

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Seminar Report 2013 Autonomous Car: Dept. of ECE, T.K.M Institute of Technology, Kollam

Uploaded by

Copyright:

Available Formats

Seminar Report 2013 Autonomous Car