ASST On MERIT - OF awake NAME CHANIORAMOULT. SARAVAN 5OWRL Req. nor HAG 004 $uey@tr ARILFIUAL ANTELLIMENCE DSUBMT 54: Due DATEr SP RVEDATES F--ao0rr SEANATURED ech. semadorn HeUrK ‘Scanned with CamScannera Write the fuactional features and tmportance of forward chaining and bactiwords and it's Pro's we Cons: Loward chainwayi Pt Ferword chaining 14 also tinown an Forward detection ov forward COD or meehod when Using an inference engine 94 Hy Forward chaining % a form of Reasoning which start with atone Sentences ta the Knowledge bose aad applia tateyence ules tn the Forward dieection to extvact more data until © goal is reached, THe fovward- chaining algorithm starts thom kKrowa facts, hukts whose premises aye Faves. thes pTOLUs Enigges all Sattstied and add thery conchysion to Kriow ib nepeated until the problem is holved: Lrogertier af forword chaining Lt ib 0 down-ve Approach, ab i mov from Bottorn tee, Tt 6 @ prow of Making @ conclusion based on Known Facts or data| by Starting from taittol gtatex reaches the goal stare. Forwerd chaining op pyeach is lomenonly cahked as we Neath ty qook. uring available data Forward chaining approach as data- driven Approady % wrnmonly used in pert System such as CLIPS, busines and predortion nuke Ayr te rns Advanrages' (Fro) Lt con be ured to dvaw multiple conchorrons LE provider a good banis of aviviag at conchubionse Zr's move exible than bacmward chaining because it does rior havea Amitarion on the date devived trem it ‘Scanned with CamScannerLactward chesainge Bactword chaining (A also Known as a backward deduction ov back ward Tearoning method when using aa Infevence engines A batkword chaining algovittin i6 a Foren of vearoning ; which starts with the gook and works backward, chaining through roles to find Known facts that supports the goak yopertis of bodward chaining: It ib Known a4 A top-down approach Baunword Chaining is based on modvs ponens taberence hole. fa bamword Chainong, the qoal ih browen tito aub-goah ev Sub-goalt to prove the Facts tye Et im coed goak driven approach, ak a list of qoolk that decides whic wuler ove Sehected and used Backward = chaining olgovitmm i used in game - theory 1 Ovtorniated theo Proving took, intevence engine, Prook aKistonts and -favious AZ applica Backward chaining method mosty used o depth - for prot Advances Cr’) Lt can be ured to daw the fist geaych eraregy tartial stated ot tre problems St ts uned to dxow ervttiple atomie Sentences ft provides a Good infeverrces tov ayviving AF start sares Risadvanragea Cems) HE may Consume 4 fot of time while deducing the stort stares. oq be not so suve about Coryect OY acwate sravt state ‘Scanned with CamScannerBl ecphain the proces of Knowledge Mepiesentation with any one heaL-tme example: Hnowhedge epxeatarationt Knowledge Representation and *aroning (Ka orwar) th the part ot ar AY which concerned with AL agents thinwing and how thinwing contributes bp tntelligert behaviour of agents Pat is Merpondible for representing information about the heol world 4» thot a tomguter can underttand and con vtidize this Knowkedge to Solve the compher neal world probhens Such as dingrronis 0 medical conditton Or Communicating with humans in catural Languages Zt ts abso o way which describ how we can hepyesent Knowledge ta avtiticial tatethgences Knowtedge Neprbentation {4 not jost Storing data Tako some database, but it oto enables an atelligents machine to learn thom that Kaowledge and experience, fo that it can behave tetelligently Mike a humane Process: of Knowledge Ke pyesentari Tree ave mainly 4 approaches to Knowledge neprescatation , which art fiver below: © Single velational tnowledger TE the simplest woy of skoving tars method and each fort about a get ot Systematically tr columns which ose, the nedational, the object is get oot Mi approach of Knowledge nepreseriation is famous in database | Systems where the hrelation sip between dhttevent entities is hepreserded approach hay hitte ope evtunity for ing ‘Scanned with CamScanner ®\inheitable Koowkedge Jn the faterntable Haowledge approach, all dato must be stored into a hierarchy of closes All classes should be avanged ina qinevolined forn ova hievarchil rnannere Heve, WE OPPY inheritence property Elements foherit valve trom other members of a cham. this Approech contains imhertable Knowledge whith shows a relation berwe| qastance and aw and it called mance nelatvor Every individual tname can neprestnt the collectvor of aMtwhutes & its value Tn this approach, obser%sk stalues are vepyesented in the Goxed nodes we will use Avyous which Point From objects to theiy values Adult male Here Aawit & ferer ave the Football Cvicket players Hes pectivehy « bot ave adult male » Hepyererited as this fyore erence inarane. 5 Terex DS dateventiol Koowledger Lnterential Knowledge approach neprerenivs Knowledge tr the form of formas fogits. approach can be used to devive move Fairs. St quaveateed the ecines ‘Scanned with CamScannerime Knowledge bared agents i the tinow A) Procedural Knowkedger froedoreh Krowledge Dpproarh uss Aral programa and codes which desiribes how to do speuitre thing and how to proceeds Ln this apgroath, one important nuhe is wed which i M- then nole. fin thia Knowledge, we Can Use Mariou’ toding languages Aven os Lrsp| Loaquage and proloy fanguoge- WE Can earY Aeovesent heuristic ov domarn Apecitic trowledge wing {his appyoach Bot Te mor nevessory that we can Nepyoent afl cose Ur this Mogroach: len ovder to opty ol these oppnonihes we need to have the Following Kind of Knowledge of nepraentartion Yin AT Syptermat Objectt All the Facts about objets ta the world domain Eventay Events ave the atiers whith goceuy feytormances St describe behaviour which how to do things Meta Kagwledge: @t tm the tinowledge aboot whet we knows Foctst Farts ove the twths about the neal world and what we (7Beny in the world: involves Krowledge about Knowledge beser the centval Component of Knowledge ~bared agents ig ledge baste Te Ib hepresented @) Mee KB. The Knowledge base is the group of sentencess [hrowhedges knowledge ts awarney py farnitiaritg qoired by emperienu 1a fairs data » situationt. AL Sys ttern has the Following components fos displaying nt behaviour by hepresentivg Ms Knowledge ‘Scanned with CamScannerRerception? Ir percepts the environment Aearningr Then it will Leann by it's Leeming companen® jo Koowledge nepersert ation n véas prin gt Te will use the Leannvng +0 heprerecbene what i bas Leannt Llaoning # erewtiont Then it will execute aciordingly te plan This how a Knowledge ib represented: with a htal time example ‘Scanned with CamScanner@Jurite a ore on following + (1) unification Ci) Funetionabities of FOPL GD Categories ahd objects, fication ir Unification ib a proce of making two diferent Logical otornie express Tdeatieah by finding a Aybstitution: Unification depends on substitution proces Te amigns Itaves 2 Literals as input and makes them tdenrical using the Substitution Let Wy % be two atomic sentences b O be the sienilar unifiey och that Hos BE, then it can be exprembed a Ontry c¥ ¥) IBxr Find the Mi for bavky (4 04 wing Cita) kee Yaweng OO 5 ye + King Goha) Substitution 8= {John Jx} i a uniter for these atoms and applyiny thid substitution and both exprewsions will be tdentical. The UNTFY alqovitun is used for Unification, which takes -wo atomic peartencts and nerorns a Unifier toy those sentences (it any) Unification iK a Key component of afl first -order tatevence olgorithrrs Lt neturos foil if the expressions do not match with each other. The substitution Poriabla ave called Most trenerak Unibier ov Mi Unification + Following ove the (oaditions boy UnFication + it Predicate Aymboh must be same, atoms ov “Predicate Syrubol Con be vribied Dot Avquments tm both expressions must tdenricale Mpresyon with dtferent fon will Foih it there are two sienitar voriabhes prtdent in si expression. ‘Scanned with CamScanner5 Foactionadites of Forir Firat ovder pyediate hoyre 1h anovrer way of Knowledge Mepresiakation ta AL. Ie iA an expansion u extmAtort to propositional, dogice Fok is sutticiently expremive to yeproene the naturel Sonquoue Krateenets fr O Concise way, Fist Order Logic (6 al4o Rapwn a4 predicate Logie or Fivad -ovder Fredicate Logics Fore ms a Jonquage that develops information about the objects ia a move Cay wiouy aad can also euros the nelationship between those objects. Fort dots not only oaume that world contain tacks like the (2) Proportional fogic but also atumes the following things in the world: eDbsectar Any physical envity thet heprsent a heal world's Aubser ts an objeto far Nama uth ah bowyi, Sevowans temas hoch od fone paper 4 place, buth os Kanuhi, enathuy eee Je Relation St can be unary , binary , terinary oy n-avy ] exe ved, round, 240%, three Aare, brothers oF et fyactioni the ser of Nebatvon among the objects i Fonction au Father of, bear tend er. 0, it donctns abovt the collection of Aymbole » atatements te these Logical consrrainds ity Semantis ‘Scanned with CamScannerAa Objecr is QM the farts qbout objets tr ovy world domara” Mese objec ave the physical entities that do hepresent the heal Hhinys doch a4 0 pevdon, name, place ec Lt is Used to nepresent the Knowkedqer It is the basic and the Vitek Ching so (see) fnowledge Yepresentation » nearoning. whereas, the Organyation of the objects tato Categories ts alto @ vital part of KAR. The cateqory i the collection of objects which axe ordered uring niations » functions, Although tateaction with the word ane place at the Level of Prdividuad objects, much heasoning tare place at the heved of Categories Thid i A note on Unification, Anctionolihes of FoPL & the Gregori ¥ objects ‘Scanned with CamScanner@Jwwite down the effective outcomes of probability. a 8 |Probobstityr Probabitty can be dehined ab & chance thot an Uncertain eveat will outs EE ta the aveneritoh ratosure of the Likelihood that an event sill occurs The valve of probobility always remains between 0 and4 that represent ideal uncertainties SOXPAL LL 5 where PUD Is the probabitty of an event A + PUY=O 5 fadicates total Uncertainty ta an event A + PLAV=L j indicates total cevtainty fa an eventAs Probability of an Uncertain even® by viing the below formula, p- Mook desived outcomes Total root outcomes, © PGA) = Probability of not happening event oPU & P(A) =1 Exy The probabiity of towing head is Ya by a coin The etfective ovtiomys oF probability t% dependent on the event. The event ib cach pomibhe ovtiome of a vaniable & called an event There Con be one ov move events lary happen Simottanequsly, There aye, few method to find effective outcome of probavitity, Conditional fobability’ JE IK a grobobility ot ocvrving an event wher another event has alveady hayperede (ais) = SAAD at is called o4 the probability of A Unde the i conditions of B+ FAAB)= Joint probability of ar 8 18) = Mavginod probability of B BH, there ove 20% of the students who Like English and Hoff who Lives English # maths » then what the percent frre, Engiish abso Like maths! 547. who line english & matins ‘Scanned with CamScanner@ independence Liqwo events ave Independent i¢ P(Aas) = PCA) -PE) «5% implies PCALB) PCA] and p(a\a)= PLB)+ Knowing A dots not mean anything about ier the outcome of Aww Adependent on event Ayindependent to bs Ear A Gretiag a B ona Face of adits 008 Bi new England fatwots hyined the gamer = 044 P(A lp) = tlA)= Og FLOLA) = P08) = i A ®O are conditionally independent given B it e(ALSAC)= POALB) «ity Knowing C tells us nothing about A given B. Ext Cy Abel ih Gtigen of england -1 «Here A&C ave independend to each other Also, there are many other ways to find the effective outcomes of Probability Uses of the probability in heal worldt Metevologists for instance, UAC Weather pattern to predict the tarn's probability. An epidemiology, Tt 4 used to undevirend tne elationship between MLPOSIG # IDK oF health efbectse ‘Scanned with CamScannera GNwrite the process s€ probabiniatic taterinie ond give an Ctample, Proabilistte inference i the tan of deriving the probability of one or move Handomn Pariables towing a speetre valve ov sei vt govinble values, for teamgle, a Berwoulle (Gnokean) Mando varinble may descube the event that Tohn hat cancer The ost tomrnon probabilistic inference tos i to tomgute the Porreiot distribution of a query Saviable qiven foe evidences Unfortu nately , even the pioMern of estirna hing the posterioy (Probability ina Velret network within an absolute evvoi ot within a constant multiplicative Factor, i NP-hard 40 gerteral eFFlcen? tmmplernentation will not be availablee The Main approaches foy probabilistic infeverve im behet vetworvs are} lr Ex pho ining the styeture_of the nerwoyks This approach iA ty pitied by the Mariable eltnation algorithm deraited Latex b Seay bored apelicationt by tnumerahing some of the fouidle worlds porterior probabilities eon be estimated trom the worlds geneured » By Conguting the probabititin mays of the world's not considered, @ bound on the ervor in the posteror pobability Can be extimateds This apymach worls well when the distribution ave extreme ag pctuy fo engineered Aystems- ayia ti a ais where the iden i to tind tn oop problem thar tasy to Conputes Frye — fthat are easy to tomputes thin com cisconnerted beliet vetwortess plex ro Kienation to the} choose t cha of Nepresentations, wuld be os Armehe os the ber off ty to find a member of the clays Fi chosen fo the Oviginal problems That w4, tind an tasy -to distribution that 4 as cose ax powsidhe tthe poreyior Hhat mus be torn puede Thus, the problem veduces to ant grobhenn of mininaging the evry ‘Scanned with CamScannerrsrocharne Simulation Tn these approachy , Mandorn conn “ore the 4 generated according to the probability disrbutiony + By Heating trae Nandom ws as a sample, the reer inal detibuhions on any combination of the yavinbles Can be etmated Sketch # Cram ples Bou GY theorme * Bayes treorm is oho Known as the Bays role of Bay sian 1 eatoning whith determinu the probability of an event with Uacertain Knouitedge, Ln Yrobability theory, * relates to the conditional frobability and the margionl prabélitio of 2 Handorn Yavio bles. Bayes theorem wos nomed qh the gitih mathematician Tomey Bayes The Bayssian intevface i an application of Bayer theormn, which is fundamental to Bayesian statistics Boyes theovm con be derived Wing product pule and conditional Probability of event A with Known event g, FANS) = PLALB)E(8) om Similiany the probability of ever B with Lo Kaown event A PCANS) = Plata) fla) Equation © x® Ko PLALB)» PLB) = PLBIA)- 0A) PCAIB) = PCBIAY RCA) } __gy ele) called Boyt hole oy Goyes theorme this ean ib basic of enor AL Systems foy Probabilishe inktrence. 9¢ shows the simglt ip between jor and tendittonek probabilitigs Here., 1 mown ar poxrevior, which we need to colcohate ond it will | das probability of hypothesis A when we have ocurred ‘Scanned with CamScanner& tre, then we cohchate the grobability of evidence PA) ~ im catled the prot probability, Probability ot hypothesrs before consideriay the evidence: Pia) - th called mucginah probabitiy , pure probabittey of an evidence. written 0 e(A; 18) = POA’) # PLAY) i PCA PCO 4A) where Ar Ay Ags--- Ag tS Exhaustive events Examples From a standovd deck of cards, 0 sragle card th drowns the probability that the cord i Wing Alea then Calcolube gasrerion probabil O (King \ Face), which means the drawn face card is 4 King woyd. PCwing |ree) = PCFacel wag) » e(wing) 49 PCrace) P(sing): Probability that the card is nye ca 3 Pltace) % Probability that a cavd is tare card: 3, 3 (Face [rings Probabivity that tard 16 face card when ayumne i is aking al Porting aM (i) we will gers PChingltace). 10%) Yo De prebabilng 3 that ® face cord 14 0 Bing: 4 tan Beliel nleworm 5 » Bayesian Belief network ik the Key Compotey technology for deaking th probabilistic events + to solve a problem which has unce defined an 4 Ylainity. we yoian Network th a probabilistic graphical model which 4 able to 8 of voriabler % they condition ppagh.” L dependencies wing a PBA) ~ i called the Ltmekihogd, in which we Consider that hypothests is ha general, we Cod write ¢(6)= POA! POIA,) sheae the bayels ule can be Aee of enutvally exclusive and AO Boyes networr, belief Aleworm, decision Network or Boywsian graph ‘Scanned with CamScannera GayMee mar wors ore probabilistic, Because these nerworks are about » built trom grobobility distributions also use probability theory for detection of Aniamely & Predictiors : Real world apghicorions ore probobilistic in nature 4 to veprerent the helabion Sghip brvovcen envltiple @venvs we need @ Bayesian network + St can abo ured ta staniovr tasks “acluding prediction, qnamoly derection, avtornuted Insight hearoning j time erits probsein » decidion mawing Under Uncertaraity LrSt contains 2 parts § © Diverred Aug die qiagh Dam) @able ot Conditional probabilities Corr) the generalised form ot Bayesian NEwom thot hepssents and Aolve decision problems under uncertain Knowledge (+ Brown as influence diagracw A Baysian network graph (6 made Lp of rodes 4 oves Cavected Arars where, each | axe Ench node cowesponding to yandom variable #0 Parable can be Continous by discretes A,B,C, 8D are nandom variables inegverended by the modes of the network wag Mode ib independant of node Ap mode A i parent of node DEB. | Aac or divecred vow Mepiestnd a casveh gieationships conditional probabitities between fandom Vaviabhess These diverted dinks ov the QvYoUs connect toa faly of nodes in graph: ane finy estan network grogh dows rot eontarn any aombers of eyehte gpaphs Hence it i Known os divected acychie graph COAM) The Bayesian Aletwork has, mainly & components eCasval Component + Actual component. Lath node to the Bayesian Network hay tondittoral probability distribution P(x, Clavemeen.))) which determines the effect of farerd ‘Scanned with CamScanneron that node Bayesian metwork M4 waved or joint probability dmeribueion % the Conditional. Probability: Joie obability Dirubutiont the callecrion # rer of abl probabilities oh on Averit i cabled vine grobabilty Hurabutyor (. Pf, 4 . Xa | = Pla las 105] Plassey en), = Plmifxree-: Kod) ns -- Plienalxnd) (Cen) Tas ih Bayes Nuke » Merwin tr ‘Scanned with CamScanner8 Discum the mechantam of NLP Ma} natural Aenguage froconingt Cube) Hatvral honquage Troveming Cir) is a broach in artificial fatelligence within aves 3 Computer Setence that focoses on helping computers to undevstand the woud that humans write and Apeans NL? ih & gart oF Computey Science, Human language and drnhiiah Gorelligeres TE te the technology that 1 ured by machin, to understand, analye, maniplate and interpret teman's fang vag we Components of AuPh There ave 2 Components bt NLP, by platural hooguage Understanding Cau) Notural, Janquage Understanding Cainu) helps the machine to understand Tad “Ondlige human’ kinquoge by extract the metadata rem ene e i Q Content such ap concepts , entitin, Keywords, ernotions, helations and Semoarie. roles. NAV mainly in Busines applications to understand the custormegy Problen tn both Sporen and written Sa nqutege NLU tavolves the following fonts y St is used to map the given input toto Useful eprese tation. LyAt 15 ured to analyze ditterent aspects of the language. Natural Lanquage Genevatron (alr tx)s- rNatural Aonquage Greneration Cue) acs ax a tromplator that CBaverts the Computerized data into natuval, fengunge i Sa My favolves Fexr planning 1 Sentence paoning, 1 ‘Scanned with CamScannerLexicak Anak ake ALES Syntahe Analysis Semantic Anal Biacovrse integration | Pragenati¢ Analysns te hericol Analyse oad Morphological t The fiat phase OF NLP is The Lexicah Analysis « this phase Scans the Aovrce code gs a Styeam of chavacters and Gnverts it into meaning tul Lexemers Tt divides the whole texe imo parogiaghs , sentences g. wordsr Ayatatic. Rowlysss Cfar sing) + Synvatic doalysis ia used to check grarnmar, word arvangernents aad shows the helationship using the word. Example Kanchigoram qoute the Ravi Jin the teak world, Agra Ger to Poonarn, do not make any sense, bo thin hemene is nejected by the syntahc analyyer Semantic Analysis antic Analysis t& coneyned with the Meaning Representation « Nimly “focvses on the literal wntaning of words, phases and Integration’ , integration depends upon the fentences Hhe meaning of Acacerce that Follo ] ‘Scanned with CamScannerSe Lrogerate Analygist Pragmatic Analysis ih the Fifth and the Last _ghore of Wie LE helps you to discover the intended effect by Seplysng av bet of Nules ‘thar choaeaue Cooperative diadoques. Ext “open the door" 4 interpreted as a heqvert tread of an order Advantage of Sit NLP helps mAevs fo adK questions about any subject and acta divert vesponse within Seconds NAP offers exact answers to the quution means it dow not of Fey Unnemary and Vawoarted information. NLP helps computes to Communicate with humans theiy languages. LE ie very time ef tiecent. Most oF the Compania Use NLP to improve the etbictenay of documenta: -Fron processes, acvracy of documentation and identity the iatermation from Large daterbares Aisodvantage sf NiPr A Lint of disadvantages of nix? in given bolowe nie may not show Context. Nah ts Vapredictabler Ant may feyuie MOTE Mey styouey FAAP th Unable to adayt to the new domain and it hey q ed function that's Why NLP uw built fra Ainghe and Wally Answer the quetions asmed by ‘Scanned with CamScannerSpam Detectioat Spam Derarion tr used to dere’ unwanted emails getting to o W's Inbox D Sentiment Analyst Sentiment Analysis it aloo naown ab opinion mining tt is used on the web to analyze the atitede, behaviour and emotiena State of the seadeye O Machine Warlationt Machine Translation is ured to tranhate text ot speech from one natutah leingvage to another natu rod Language bpelling, Covvection! Micyosott (o-ovperation provides word procensoy Software Like Ms-word, Powerpoint for Spelling conection, Other applications be Like speech Pecognitia, chatbot, intormahion extyacton, NLD ete- This 14 Alatuvet Language frocening - ‘Scanned with CamScanner@l How nobetics ave used tr autoenation Procents @} Avtornation Provess i= Prom avtornitition streaming a Aystem by removing human taputs which decreases evrors, increases speed of delivery, boosts quality, and Minin ys LOA Ond Aimglihits the burinen proce. Tt incovparatr softwares tosls, peophe and procewas to create a cornpleth automated worAflow This automation could be done by the yobots by automating rhe proces by RPAw Robotic Proce Avtornation (ReA)y So Dole ice nu Sera ttan Robotic proen Avtornation (RPA) {4 A fofbware technology that makes ie easy to build, deploy and manaye goftware Sobots that emulates humans actions tnteyarting with digital bystens and bofwaves Fuse hike people, Software yobots can do things MK understand what's oa a seen, Complete the hight Keystvotins, Mayigation Syterns) idencgity ond extracr data and pettorm a wide mange of debined ACriovy but software vobets can do it totey and more consistently than People, withoot the need to get UP and Arvetch ov tare a cottee bean worki i of Robots in Qvtemationt 4m ovdey to avtomare the proces , Che Robot shall do the followrng Sheps. Robotic kenpors measure Hobot contiguration /eondition moment and fend such tnformation to hhobet Wertyolley. grabs bensoys shalh do the job of percerving mente Tae will be wed to automate ‘Scanned with CamScannerThe fore Aendoys will be used to Ht in a precise order and insert of machine parts by using fovce fervor A Nobot can tasert pars that have the phases after mnatehing they phos, an addition to Senply inserting them, £t Cor avtomate high — suctt jobs Various sensors will anelie the problema of Various Kindi but only Actuators can etted the sensor's input after anolygiag and processing the tagute Me conrroilers will provide necevary intelligence to contyel the enanighator / mobile noboe+ te with P1CH the bertovy tnformation & Compute the (ontyol commands for the actuators to ayy out the Soeutied tasns Actuators wn be of diflesen pinds mechanical devicer, ot combination ot tarious elechya Bho as Motova, wives ere- The whole proc lan be stored tn the stovage devices. The Aasenbly maniplatoys ill moniplate the Herd wares 2 combine therm to avtornate the proces Aubert 4 Manipla tor A Typical Automahen procs when yobuts a included a ‘Scanned with CamScanner@ Explain about deiveyleas - veichle systeen with example LA ele driving Cav alko Known OF Gn gotonomour cad, driverlers cor ox robotic Cay (yebo-tay) 1% & Cay incorpowting gehivlar automation, that 6 a ghouad vehiche thet is capabhe of Senaing ity eavinonment aad moving safely with Lime or no hurnan trput seit driving Cavs Cornbine a Woviety of hensoys to perceive Hheiy Surroundings, such WA thermognaghic cameras, haday, lidav, honay, Ps, odlometry and trertiah measurement units Advanced contvol byrems interpret Sensory infoymation to identaty Approptate navigation paths, as well as obstachy and hedevent Siqaiage. Gonryoh methods based on aatiticink tmelligerdeecan then be wsed to eavn all the gathered Aendory Internation in order to contyol the vehike and support varrovr autonomous dviving teats. Aso future technology , they axe predicted to have L @ compvehensive ieypatt om autornobite industry , health, wealth 1 vYban planning , etldas ing automotive technologies Suda ay connected velwdey and shaved mobility, Selt driving evs ov driverkey cays tyom future called connected, Avtonomous , shoved and trathic, ‘osurance, habooy market and omey # Vogerher with they ernevg vehihe, chectyitication mobllity vision dlectre (case) mobility Avtonomy im vehicle is often Categors toa byptern developed by NY Undty stood a», ged in 6 Levels, SAE taternarionak (64x). at Cay NO dvtomathon. hands 0a / shaved: controls ‘Scanned with CamScannerhovel 3 - eyes oft devel k= rind oft devel # - Steering op tional develo fhe automated Systern tues warning and rau momentary intervene! bot has no sustained veliche contyol devel “Hands on The driver and the automated System shave Contyol of the vehicle, Exameles ove sypterna where the dyiver conrvoks steering and the automated System contyolr engine power to maintain o ser Speeds OT engine and brake powey to maratain and Vavy speed 4 evth-ak “Hands ott” The avtomated system tows full contyol of the velvicle 4 accekwating ; drawing e skeevings The drivey must monitor. the driving ard the grepared to intvevend Tenmedigtely ot any bene & the aotomated system fails to nupord rope lye The shorthand “hands off” i nor meant to be tauen Litevally. coaract berween hand and wheel w% often mandarory doring SHER driving, ko Contivm that the driver i Ready to intyevenes The eyeh of the driver might be mmonitoved by camera to contiym “Yat the dviver is Keeping thely attention ty tyathics ory “Eyes ott” river con satAy turn they attention wou, trom 1&4, the driver can texr oy watth a Nim ‘Scanned with CamScannerthe dvivey mum Mill be prepared to intervene within some fimited tine, Specified by the manufaccurer, when tolled upon by the vehicle to do $0. This devel of automation can be thought of ox a co-drtver ov co-pilot that's neady to alert the dviver ia an ovdely fashion’ when swapping they turn to drive eveh-4i- Mind off The velwde must be able to safely abort the trip xr Show down and park the Cov A yobohic taxi of a robotic delivery service that covers selected Wcariom tr an area, ak a speutic time and quantitverr heel 5 Steering wheel optronah No hyman tarvevention at al(- A Yobotic vehicle that could work at alll Kinds of Sovtacts, all over the world, all Year anound in alk weather Conditions. a kicabions of dwuerkew cansy 1 Ocade's Avtomated trucks ® wheds co boogie belt driving cot & Jule - Model 3 ,Modeh Y, Modeh Ay Tedda~ Modal: LiTheart ane the dvivevies in detail Cavs 205 THE ENO, ‘Scanned with CamScanner