eoo?imtion 'Driverless Autonomous Vehicle Tester Prog ram April 2018 Introduction Waymo, formerly known as the Google Self-Driving Car Project, is a self-driving technology company with a mission to make it safe and easy for people and things to get around. We're determined to improve transportation for people around the world, building on software and sensor technology developed in Coogle's labs since 2009. We're committed to developing fully self-driving vehicles because we believe that this is safer and better for everyone. Annually, over 1.2 million people die on our roadways. In the US alone, traffic collisions kill over 37,000 people a year and that number is rising. In the U.S., 94% of crashes involve human error or choice, and this is one place where we believe we really can bring technology to bear. Fully self-driving cars could also help people who can't drive-whether they're elderly, blind, or disabled-to get around and do the things they love. After nearly a decade of working on this technology, 5 million miles driven on public roads, more than a billion miles simulated every year, and thousands of comprehensive tests, Waymo has introduced fully self-driving ("driverless") vehicles without a test driver in metro Phoenix and will do so in other jurisdictions moving forward. When the automated driving system' of these vehicles is engaged, all occupants, including Waymo employees and members of the public, are passengers only. These driverless vehicles travel within a defined geographic area in the local jurisdictions where they have already been tested extensively. Separately, Waymo also continues to have a separate fleet of self-driving vehicles with test drivers. The documents below supplement the overview of how we design, test, and validate our technology in the Wavmo Safety Report. 2 AUTOMATED DRIVING SYSTEM. The hardware and software that are collectively capable of performing the entire dynamic driving task on a sustained basis, regardless of whether the ADS is limited to a specific operational design domain. Table of Contents I. Wayrno's Application for Driverless Testing to be Submitted to the California Department of Motor Vehicles II. Waymo Conta(;t lnformatiQil Ill. Supplemental Attachments A. Evidence of Insurance B. Copy of Written Notification to Local Officials C. Waymo Two-Way Communication Link Monitorinq D. Wayrno Fleet Monitoring Overview E. Intended Operational Design Domain of Waymo's Vehicles During Driverless Testing and Operation F. Geographic Area for Driverless Testing (California) G. Law Enforcement Interaction Protocol H. Fleet Response Specialist and Rider Support Agents Training Program l. Fleet Pesponse Specialist Training Outline: Week 2: Classroom Presentations, Emergency Procedures, Supervised Fleet Response Specialist Practice. Daily Assessment Week 3: Supervised Fleet Response Specialist Practice, Escalation Simulation, Final Assessment Ongoing Training and NotableTraining Tools{MethOQ!:i. ?,.. l~ider Sugport Ageot.Iraining Outline 3. Waymo Fleet Response Specialist and Rider Support Agent Training Certifications I.. Waymo $.9J~ty Report J. Qmy of Wayrng's Corporate lnforrnation Filed with the Secretary of StLC ~NAMllYJifutiRFU-HiNv'numT------------------ WnymoLLC J600 Aolphl:theatro Parkway MAiLtNG AOOOi!ito Of b)FfCtmtff HtOM s:t"ReeT MD!U!Sa~ --~.~ii;AT,;:~.J:l5 ~:0~IPOOPE em SlRiifi',6:01~-·-----------­ · · - - TIJLEPHONF. NIJMBEu~ Mounl~in View - - - - - - em - ~ww _ _ _ _ _ , •• 100 Ml\)'liolil Avenue CA 94!l43 CA 94043 ~-,;;.,,;,.,;..----,,i>,.ii'cv l"oca- -Pacificu .PREv -- MQ'fi:El-Pacifica PHEv IJOOEL Pnc!l!ca PHilv ~- 2C4RC1K74HR534652 :WJ'I Chrysler Yf.AH """' Paoiflca PHBv ViNNUt.ttn~n IMK"ff MODEL :i,2 Chrysler MAKE Pacifica PHEv ZC4RC!K7:illli534644 ____ --·· --·· _ ,,_ .. .. ,_ ·--MAl«, """" 2017 -- """" 2017 ··-.. ·~------ 9E4C"" 2017 ""'"" Pacifica Pllllv Chrysler 7,(}!7 ....... "'""'" "'W5~1--··-·-~ Chrysler Pacifica PHBv ""' J:IA'i(G~·--·- IM5fi&1. Chrysler Pacllica PHEv ""'Chrysler "' Moofit .. -- ----···----'---'----Page 1 ol3 v Pacillca PHE IYfll!ll 1111111111111111111111111 l'iJi!......,. 7XJT281 ~ti!NUMBI:!R 8.173402 ~NUM!m~ 8572902 fit.Ai'fl NUMI!lm 8513002 ~1 lATE NIJMiiliR f aw~ ISS1.l€~ WITiriMillR'- CA 2C4RC1 K74BR534683 STATEI$5U£0 ViNNUMiif!n CA •.. VfAR l017 2C4RCIK77HR5:14676 !!~TATE leOOEP -~~" CA :zc4RCIK7XHRSJ4686 $TA1'l'tta6UED V1M »UMIH!Il CA $TATE' ~'35t.!iiO PLAniNVM.iial STATEls-sti!W CK6()752 AZ AZ P\fiiliHl.IMilim-- f's'fi.1'R IYU£0 CK607S3 PLATE~ CK6ll754 S'fATI'li&Sill!U PLAtE Nw.ffi!UA STArE ISSU!m CK607S6 Pl,xm NUMBER CK60151 PtATii NUM!l~E:R CKM758 PLA+i MoM CK607S9 fiiu.n;;~R. CK61l760 1\Z AZ AZ SWI! 0111\NO AZ ctml2b CK60796 2017 Chrysler Pacifico PHEV """""""'" X'4RCIK7XHR69570J VLAfG NUMIU'J\ $fAl~ I$SlJF.D PLATE MUMBUR CK60799 PC~'ffi-"NU~- CK74903 iilA"tl£ NOOfiliFf"·'-- CK74905 ~~MR CK74907 PLATE NUMiisR CK74921 PLATE M!M~:~ER CK74926 AZ StATE !SSUEO - - -~-- ·-·--·~ fviNt;rUMB11rt"'""""'"---------· 2C4RCIK75HR534661 V1NNUMEI1ifi AZ STATE IS$UEO AZ Wfil:l Chrysler . '-""·-·---·---~- .. 'II!AR ~- Paciflca I'HEV '--'·--~~ -· MOblt.l, Chrysler Pacifica PHEV Pncifleu PHflV Ch1'ysler -- MAKi-· ~~~--~- f>ncitlca PHEV ------ MOOF.L MAKi?--~- Chrysler 2C4RCIK72l!R5'l4696 - -- 'MOOI;L _ l'acillca....PHEV _..,...... ....... M6bEL~ 2017 Chrysler Pacifica PllEV MAKt:: MOOSL. 2017 Chrysler PaoiOoa PHGV """ 20!7 -MAKrf""""'·"-- ~·-· YEAR YEAA VIN NI.IMfl~ ;:ifroa YI!AA 2017 2C4RCI K75HR534692 vrNNUM&im 2C4i~C IK77NR534693 -.. .. ·-- Pocifi.a PIJRV " 1 PHEV M{}ufJ. Chrysler Chrysler 2017 2C4RClK71 HR534687 ........... 2C4RC IK78HR5:14685 AZ AZ l'aelfion PHllV ~ . . .·--·····--·--·. ·-~-- lvoo··-~-- MAJ(I:--~-~ STATE 1$fU16!0 STATti tSSU'Eb- I"""" fYifA1f _ _ _ MAKE-·"·-·--· rM6'6EL"-----·--· YEAR CK60797 Pacifico PHllV "'"'a Plllliftco PI IllY ,_ 2())7 STA!emS\JOU I~"C'. ~-~·~-- -- --· Puciflcu J>IIEY Clirylller 20!7 ve:M 2017 ~7 Pacifica PHEV ~-··-·-"' IMAI)(3) 6, The autonomous vehlole.ls capable of operating without the prmy andDefinffloM for Terms Related to DriVIng Automation Systems for OnRoad Motor Vah/t;les, sl!lndard J3016. CVC 227.38(0) 7. A copy of a taw enforcement lnteroolion plan will be submlttod to the California Highway Patrol within 10 days of application approval, and the lntemel web site address where lh~ law enlon:oment Interaction plan may be aooessod will be provided to all other law onforoament agencles, flrst responders. fir~ department and am•rgency medical personnel within the vicinity of the op.~rational design domain of the autonomous vehicle. CCR 227. 38(e) 8. Remote operators have completed training sufficient to enable him or her to safaiy execute the duties of a remote operator and possesses tho proper class of license for tho type of test vehicle being operated. CCR 227.38(f) 9. Passengers that are not employees, contractors, or dasignoos of the manufacturer will be notified of what p.~rsonallnformatlon, If any, may be r.ollected and how It will be used, CCR 227.38(h) 10. Upon recolpt of a M~nufaclurEir's Testing PormH to cortdu<>t the tasting on publlo roads of a vehlr.la that does not require a driver, data rolalod to the disengagement of !he autonomous mode Will be retained for the purposes of submitting an annu.al report to U1e department. COR 227.50(s) 11. Any collision originating from tho operation of tho vehicle on public roads that resul(i>d In tho damage of prdperty or In bodily Injury or death shall be reported to the deportment, within 10 days, CCR 227.48 1:.1. Autonomous test vehicles will not bo permitted 1o operate on public reads when members of the public that aru not ompktyeos, oont,actors, or designees or the manufacturer are cha1ued a tee or the mantllacturar receives camp.~nsation for providing a ride to members of tho publio. CCR 227.26(f) Page 2 of3 g__ _,_. """"-' ~. _5&. -~ _?if__ -~ OL 318!NilWU-lll11) WWW 1. Evidence oflnsuranc&, Suroty Bond (OL 317), or Appllcatfon for S<>lf·lnsurance (OL 319) In the amount of five million dollars ($5,000,000), CCR 2.27.04(o) · 2. Copy of written notlffcatlon to local authorttlas, ae daffnad In Vahle!• Code sellllon 365, for each jurisdiction wher<> the va~lole will be tasted that Includes all of the Items idantlfll'lROVISIONS. ACORD 2S {20161031 The ACORD name muttcgo ate rog1$tfll'ed marks or ACOOO AGSNCYCUSTOM!R 10: 10;:25',l94=;:;;:;;;:------LOC lh _san FrancisCo ADDITIONAL REMARKS SCHEDULE ADDITIONAL REMARKS THIS ADDITIONAL REMARKS FORM t5 A SCHSJULE YO ACORO FORM, FQIIM NUMIII!R' JJL FORM TITUI: .E~rUfl<:nte _of LiabilitY Insurance __ •..... '' ' PERSONAL INJ\JRYlWinl U~TATION eltX.'lJ&.MIENl', I'OUCV OO&R; MWn31(151(1(00101!2011•0BI01/m111), 0!.0 RE.PUStl¢ INS!.IMHCE CO., I.WI'l'.:$10,000.0001 I ' ADVER11Sf00 li.JJtmV LMf, EXC\.Ul.i£:00 ACOOI>101 (20011101) @ 2008 ACOOO CORPORATION. All rlgllt$ -l'VIId. The ACORD llMI& ttnd logo-lint regtrumd I'Uirk9 Of ACORD B. Copy of Written Notification to Local Officials Notification content enclosed on the following page. Rot Waymo 1Loa Altoa ootrtat:t lf~ijll ....... ---·-···-·"""--·-- .. ; ~~~~"-'·-----~------------·------~--------------·----~-----"""""""""""•••• - .,,,.,,,._______________ ,,,.,,,.-~~o;""""""".."' lfi!Wo'h\l" f II 1l);qtmlliiiiiJIIulll«<•ol,IIIY ce M111 ll~WW!l ••• • -~..........,...~1!1!~" ·~~ w""' MW1li'!ltO:I!Y£101, wq'!Win~ll IQ-#tr#I\Mi ift¥011!!1t upifJ~ ful filiJWtndm!rmro 81' \li'itjmn.. llfytI!hll~, ~~~~:tr:=:=l!ri':.C:n~~~~~:::-~IM!~!IIiV~truktl'lQWM't.~lli~W!It~to.mto~l~/lflfBl:tMai!MaldtM«w!l\:f.IIQn,IW!~ ~oflll\ll'ilnlii'ldMfi!MloMot#i!l~~~~~ll'lplollliiC!\l~mtV,lfi~IINiuplil'dUIIII"IIi'fllll!'lild~~IIWIIllllllilul&~l'lll!opt!~le,lli!dJlih!l(fllltylb!pmt'/ii!51~d~!MU.5, ~~u~r~s~lf®loiOO!itwflbl1, :=~~==~'e=~~=~~~~~:.t:::::~f~==~=-~~:=:=c~=~~~:.':~~!~oC::~~it)lltl ..... (mlft~r~I11HI'Wfth.WI'Ml~.wl11)11!liii-~I.Jiw~li@tHU!If!Pi~--~~~~~~~~~flllV.k.liiiiMIQII!crVOOIPI18~MdJI!itlfXJ*Iil~,W~Wfltllltfw-!!1'tJliiii!!UrlqlfliMI:~Mihlt :!Miililt.lflll'IIIMNI!ditd. /wtuMWI!iiPJ,WII'tll:itlllk'\!lto'~mttlttMllln~iJI'ilOfM!IIIil'/~iltMilt,~u>rP$1111iilim!IUIJJIMtl\lltlle_~llilNifdMIIl~eliWI~11111rotii!IIOQiM\;IIte1Jf«U.il'tllOI!ftl.!lldM~!l,W(Iilmt ~~~~li£UIJI!t11\ff~Wdlldiig'jk1-llie-'~nflffin~·Dll)'ru",lt!!$1~i.C;Al!o!HllltJ(\111U.S. ~IJIK;~it.o'wm~~~~n~mu. I(HIIJhi/IJ!liJHlflllit~ll!®i:llldt~ll!l\.-llMll\lltll11M!Ij$U1111ilfdl.ittiQU!WVdlf~-~itfftllfA'~~~.-Ihbii'DWIIpJltiWUIIllf--W4~loakrt!ltl"~_,.oUDJtm\l\i;~HI~HihilWit.'Mt'Milrili(llf )'oU!ll!tal'j. OtUII'dl,_lli~!'fflt~Wit'M!I$tlldJi111tllii-WI~~~nNIU~Ik'l~~~ll!ldilliVIIIf~!'!llllllrd~jfuflt;m.f«}I'WI'I~tm.iliiiJ~I$.>Will'dl!U!ifhlJI~p~~~~~Q,\Ihll fni\WII!IIlilllft~, MntM~~ps,""!!'~~wlldl!lilllkt$1~•-r~ill!l}ltna~lttlliOifii;Vtflll;Mlillll11>i1!!illlfllilllliMA!h.llHilll'ivl~l!i!lllltft19tlli!~nrMlllo.blAA~IIII'IWIJlf09•11m.'"'OIIr~u~lli)II,N!IIO•I M--~...,~~~\W!Ml-pycllliJJ#IMI~IMti!Mc0i:fll'flll. ~:-==:~~~·11!Wlflllfrilmwi,IM'ifllil~{lrltif!IO[Ipliulll>~IG!Itllll'SUioml:ll~ui.WI!:!fJI!,~-I*t4~~10\llll4d00~Uitm~IOWWU'fhltfWIO!IliJeallllh ~:~~~~=-~=:llllt~li!Ot:~wr,•lit96!i•~~~--Wfitwllll'/ntr41Mi1il tlilpW.iommhfflmo11i1PbQill\ii!,~'wtP111f11Qlc\141, ••- Alim1WiiM«lllll~f0!11,~\liill~~~~~•-~-~~~wt~:~~tGI!iltvl._ ~~~I*J\JJ!\IIW!Ioo·~•'41\ld~'UllltfP«'\\rM!,Wii.IW1llil)'lliiwiletNWUI!miiW{A!UMI3).AJl!iP~urola.~~!'!M ~~~~~~~~~~~llilf~II!I!~WI!UtlM. ~illll!'fumj)IMJill!nl!IOl:I«MMIMtt, WlliiiMootl!ldl'l\,fl$Y&~IIIIW'I'_t~liiH'41hl$dwn0h'f14M.'~l!ll=-~l\ti-'IWIW~l'fMu=tffl~l~.ll!NIOMVlli'llf(lfilt111Lt-@~~16!MihiiiWt""~WliiUftb~ ~i!IW~~d'll'i!ltlg:~W'~~~6PiililjldO~tirJ!.!t$f4if\!llffm!ilm!ii!PJrf Mrttrm•lflllnlf.lllolltttlilif~liiM)'ol~.t $\ftlrW~!f"®M0011litftl W/1$111,\!M~~ ~~~-WWI'Al!l'ffllfpuiii!IWI\yloot.a'i'l'll'lliiK!:I!MffitW!wii®PI~ll'«ilii.IW~I'IIf(Uil(M-InkwtlmlotlkllilllgiWillildilf~llll¥11iA!t~i6'1WWNf®lql!lltllitM, ... 11!$11~f#ll, lt.Riifal ~m;:rll'<:f-qr Wilf~'Jm Dnt 1.1£ ~111\IIWI M!/.1.\t!fb, n1t11111100M ~fl~ laiJirltJ l.imi cu !IJ!Il1>111'4lh Me eyp~~~~nt tl'lbWfilllmQll. lliMIIWIW~!Illllll•1iib~!l;p u~ rum a~ fooo~r Md~M~Ih(;ll~WWJb~. Mfll)llliml,immNI!IIt!~0MI~I!Wlltlflll~lltjw'jo)!lftWtii~0$$1yllilll~l11101Mt«<~;, P!tli!ljjtilml}rnll,l'fllfitWa.wll•lllll\fiiBIIMri!\f!i$!1111~1MfJii~1PQbltQI/WIJ~·!Mj\MI~$!iKHlillf.. .ll:~l41twinM0011!1i,tll'loli,l!~cm~lliiii:Oiflllet,MliOOIJiili~~(Jrtfcl~j!~i l/ll~ldt T..,PI~ \!lhll:h !M~ V#II~IOOWIW# (Aflrii1S~, A~, 1'!111 oflhM o~eMioo, 1\'11 M;vo diW;ribWi\lll~ilm~«'o~a~r.lleiWto'IM:lW!~BtWNH.~ih~eutolf\1!oAAQ't10/11b, AM.UimJ,\'Illll'llliMMkijl~i-Gljd~I~W/1)1!11Jil''WIMQ~il'I~Oalii!NJ!114hM!I,IodiP!llrlijiM~M.II~II'I«~IIM¥Mil~ldlliWidf«tpOnwmmllrtttklliwtt!.ll. ~lrm>1l~ITt~aj~~lo~~IJl1, =:!:fp~=~~==~:~;r~"F~=~:f!t*!':'~!;~~rJ;::::=~;:~~~J.~:~~~~=~~~~wm nd~you~!ltttij, .. =.:mmr.!:s~~t, 'Ovt!Ufllf,WIM-~UI'Wiitll~ll!ll~J!rnl(!lll(ll&l1d~llltlll\'illl!lnll!ilil1lflffll1ilk>ll!br~lprl~~jhnr~po!llhoi .. WtVAAAIIWIIJt'I')'W~IIJ8!1b.1~)WI~~~~IIlli! MPt~~I~Wli'NwNWv.wl11!1ft<).$~htili!l~ur~~~~~~WIIWIInl\refl9t~tPI®tl~,\\fltlr~llllll$:ilt!!HwPM:IAllhwalb$atMioiMm.wu~ti.iiW!I)1!W,oortrllll~~u!l-tWiun~rr-.!lllllae~ !l!ililrll,j~~U!WII5''~Vhtdf!IMMIIIii-IIPP~~~~~~tlPlllilllip!li]~IM'nL .., l!! lhflrMitm,!t)'W llmrllWqllNlllf 1.!\#!f! f>wty Weymo 1City of sunnyvalq lr~~Q ......... 1Mnlt~CiUOiftM'JW111($ till'll,t IQ.$1J'Ukv.ftj~ nl\l:flmjjO'iM Alljllilltjlfli».IWlllNdliJ . . .liltl~~~!llvmllirnllllitllll!lll-iii.Wi!l}'l"!*. AIIYIIt~~imlriitd&lllltl~lkll.):ltM~CIIYI1iqidlii-.,\Mlll$1r~~i.t:AAI!IIl~~~Mil~lll0lti!MW!ffil'l«li00#001lUr'itlr411MilGIM~i!J~etrvt»"lllllintri!tJlrtt)llO!IfiM• t'l\ljfl\"#dlllt•"~~*.""'. i.~llUHI~II~IIlll~iumCI!lr~~lilliMv.l!hilillprullllkl~~llhitwdtemdiM!rsll~~.t4Mf·tll~~l!llttomi~.ailll~bWoiWul1ktMIIwm1!lWIII;~.-m ~Gf!«~lllt~W~Gfour~.ti:t~%4111,\W~li~~U~p1\t;llW!l!lrlllll\\lihiRli'l\JIIr'stlf··O'Jollh'&lirllti~~lllm6tlali/Xaill:t,'WIOOllMp!lll'lr~~·..-. ~lliliftl'"'!mlfuol:jj iM«Wf111Jijilf~M l!lltfr~lul~llltlrlllr~WIIIbq.~IIIJ~IllWIC.JfitlMViltll~A\Ilii!IQfmlllll~b\'QillUPf4RUIIh\I'Mtliho)'ftfll~lilln6r«'tlii!UWflltllltm~JO!~l'Oilllt,W.\\fl/mi/y}W ~~J:'::.'IW,Iolrl\\i!l!eml~lilw~UW~W!Wffi~radl~n;.lllo/IMVHjio)'•rf~Ut511QM, ::*)'il{l, f&!CMMUI Hlt./ldnflui;~!Jll>Jil.'l \.Va,.,w C. Waymo TWo-Way Communication Link Monitoring Every Waymo vehicle has a two-way cellular communication link, with redundant cellular service, for connecting with our Fleet Response and Rider Support Agents.' In certain emergency situations, the Fleet Response Specialists notify the Rider Support Agents to connect to the passengers. In these situations, the Rider Support Agents are trained to promptly initiate communication with the passenger. The Rider Support Agents are also notified of irregular trip situations through the Rider Support tool, and are trained to connect with the passenger upon receiving said notifications. In addition, if at any time the passenger is looking for assistance, the passenger can press a button inside the Waymo vehicle's second row or by calling or chatting with our Rider Support team via our mobile app. Rider Support Agents are trained to rapidly connect with passengers and initiate real-time voice communications to assist passengers in the vehicle. If the Rider Support Agents cannot connect through the car, the Rider Support Agents trained to reach out to the passenger's cellular phone. Passengers' cellular phone numbers are stored in the Rider Support tool. D. Waymo Fleet Monitoring Overview Before deploying our fully driverless vehicles, a Waymo technician ensures that each vehicle is ready for operation and puts the vehicle into driverless mode. Waymo has two separate teams that continuously monitor our fleet while in operation. First, our Fleet Response Specialists possess valid drivers licenses and are responsible for monitoring the status of our vehicles in real-time as they travel on public roadways. Using a virtual tool, they monitor Waymo vehicles during all self-driving testing, including testing both with and without a human driver. Additionally, our Rider Support team, which provides customer support functionality for passengers, is available to communicate with passengers at any point in their trip. 3 The definition of "remote operator" in the California DMV's Driverless Testing and Deployment Regulations (CCR 227.02(n)) allows (but does not require) operators to "perform the dynamic driving task for the vehicle"¥ otherwise known as "remote driving" or "teleoperation." For safety reasons, and because Waymo's vehicles already handle the entire dynamic driving task at SAE Level4, Waymo neither has such functionality today, nor do we intend to moving forward. E. Intended Operational Design Domain of Waymo's Vehicles During Driverless Testing and Operation A duplicate of the information is provided in the Waymo Law Enforcement Interaction Protocol. The operational design domain refers to the conditions under which a self-driving system can safely operate. Waymo's domain includes geographies, roadway types, speed range, weather, time of day, state and local traffic laws and regulations, and other conditions. An operational design domain can be very limited: for instance, a single fixed route on low-speed public streets or private grounds (such as business parks) in temperate weather conditions during daylight hours. However, Waymo intends to have a broad operational design domain to cover everyday driving. We're developing self-driving technology that can navigate roadways in a variety of conditions within broad geographic areas. Our vehicles are designed with the capability to drive in inclement weather, such as light to moderate rain, and can operate in daytime and at night. Waymo's system is also designed so each vehicle will not operate outside of its approved operational design domain. For example, passengers cannot select a destination outside of our approved geography, and our software will not create a route that travels outside of a "geo-fenced" area, which has been mapped in detail. Waymo's vehicles validated for driverless testing include a Level 4 automated driving system under SAE lntNnatj,onal's Tax0 nomy and Definitions for Teem~ Related to Driving Automation Systems for On-Road Motor Vehicles, standard J3016 (SEP 2016). This system is what enables the capabilities of our fully self-driving vehicles. Our Level 4 system includes the software and hardware that, when integrated into the vehicle, perform all driving functions. Waymo's self-driving system is designed to perform the entire dynamic driving task 4 within a defined operational design domain 5 and has the capability to achieve a minimal risk condition 6 : the ability to bring a vehicle to a safe stop, without any expectation that a human driver take over. In contrast, systems at a lower-level of automation, at SAE Levels 1, 2, or 3, are required to have a human driver take over from the system when necessary. 4 DYNAMIC DRIVING TASK. Means all of the realwtime functions required to operate a vehicle in on-road trafFic, excluding selection affinal and intermediate destinations, and including without limitation: object and event detection, recognition, and classification; object and event response; maneuver planning; steering, turning, lane keeping, and lane changing, including providing the appropriate signal for the lane change or turn maneuver; and acceleration and deceleration. 5 OPERATIONAL DESIGN DOMAIN. A description of the specific operating domain(s) in which an automated driving system is designed to properly operate, including but not limited to geographic area, roadway type, speed range, environmental conditions (weather, daytime/nighttime, etc.) and other domain constraints. 6 MIN I MAL RISK CONDITION. A low-risk operating mode in which a fully self-driving vehicle operating without a human driver achieves a reasonably safe state, such as bringing the vehicle to a complete stop, upon experiencing a failure of the vehicle's automated driving system that renders the vehicle unable to perform the entire dynamic driving task If the Waymo vehicle can no longer proceed on a planned trip, Waymo's vehicles are designed to be capable of performing a safe stop, known as achieving a "minimal risk condition" without any need for human intervention, which is a requirement for anSAE Level4 automated driving system. This includes situations when Waymo's fully self-driving vehicle experiences a problem that prevents the automated driving system from continuing the driving task or when environmental conditions change in a way that would affect safe driving within our operational design domain. Waymo's system is designed to detect each one ofthese scenarios automatically. In addition, our vehicles run thousands of checks on their systems every second, looking for faults. Our system is equipped with a series of redundancies for critical systems, such as sensors, computing, steering and braking. Our vehicle's response varies with the type of roadway on which a situation occurs, the current traffic conditions, and the extent of the technology failure. Depending on these factors, the system can determine an appropriate response to keep the vehicle, its passengers,' and other road users safe. During driverless testing, the intended operational design domain of Waymo's vehicles will include the following roadway types: • • Freeways, highways,• city streets, rural roads, and other roadways. Parking lots During driverless testing, the intended operational design domain of Waymo's vehicles will include roadways with posted speed limits up to 65 miles per hour. During driverless testing, the intended operational design domain of Waymo's vehicles will include the following inclement weather situations: • • Light Rain Fog During driverless testing, the Intended operational design domain of Waymo's vehicles will include all times of day and night. Waymo will provide local jurisdictions with information regarding the geographic area where our vehicles are involved in driverless testing. 7 PASSENGER An occupant of a vehicle who has no role in the operation of that vehicle when the autonomous technology is engaged. A passenger may summon a vehicle or inPut a destination, but does not engage the technology, monitor the vehicle, or drive or operate the vehicle. A member of the public may ride as a passenger in an autonomous test vehicle if there are no fees charged to the passenger or compensation received by the manufacturer. 8 See California Vehicle Code§ 360: "Highway" is a way or place of whatever nature, publicly maintained and open to the use of the public for purposes of vehicular travel. Highway includes street. During driverless testing, Waymo's vehicles may transport the following categories of passengers: • · Waymo employees, contractors, or agents. • Alphabet employees, contractors, or agents. • Alphabet affiliate company employees, contractors, or agents. • Members of the public as passengers during testing, without any fee charged. ttomain Constraints Waymo's intended operational design domain will not initially allow for driverless testing under the following conditions: • • • • • Snow/icy conditions Heavy rain Flooded roadways Offroad One-way mountain roadways During driverless testing, if any of these conditions are encountered, Waymo's vehicles are designed to be capable of achieving a minimal risk condition without any human intervention. Controlling the operating domain of its driverless vehicles is a part of Waymo's dynamic testing program. For the purpose of driverless testing, Waymo may choose to change domain constraints for some or all of its vehicles at various times. For example, driverless testing may be limited to: • Certain times of day • Roadways of slower posted speed limits than 65 miles per hour . • Certain validated roadway features (including freeway ramps, merge lanes, turn lanes, intersections, construction zones, roundabouts, cui de sacs, roundabouts, covered parking lots, restricted speed zones, and rail and light transit crossings) • Non-inclement weather conditions. F. Geographic Area for Driverless Testing (California) Waymo plans to conduct driverless testing 9 on roads within the California Bay Area communities outlined in the boundary map below with the vehicles described in Waymo's application. These geographies are part of Waymo's current operational design domain. Each of the covered communities will be notified of the date of driverless testing, prior to the start of such testing in the respective community. Additionally, any expansion of this territory during testing will be preceded by a notification to such covered communities before it is submitted as an amendment for review to the California Department of Motor Vehicles: 9 TESTING. The operation of a self-driving vehicle on public roads by employees, contractors, or designees of a manufacturer for the purpose of assessing, demonstrating, and validating the automated driving system's capabilities, . [Emma wanuugcl Skim. L?ipb?ka! Law Enforcement Interaction Protocol Protocoi endosed on the foHowing page 1. Communication With Waymo Rider Support Through Dedicated Telephone Hotline Established for Police, Firefighters, and Other First Responders During Vehicle Operation A. Wa8mo has established a toll-free telephone hotline dedicated to allowing police, fire departments, and other first responders to communicate directltj with Wat~mo's Rider Support specialists and is available at all times when our driverless testing is taking place on public roads. This phone number is provided b8 Wa8mo direct18 to state and local police, fire departments, and other first responders. a. Wa8mo has created a Rider Support team to help answer questions for our earl8 riders. These specialists can be reached, bt~ either our passengers or police, with a button-press inside the vehicle's second row or b8 calling or chatting with our Rider Support team from the mobile app. Our Rider Support specialists can speak with riders during the regular course of a trip or assist in case of an emergenctJ. 2. Where, in the Waymo Vehicle, to Obtain Owner information, Vehicle Registration~ and Proof of insurance in the Event of a Collision or Traffic Violation Involving the Vehicle A. Law Enforcement and other first responders can obtain owner, registration, and insurance information for each Wa8mo full8 self-driving vehicle b8 calling our dedicated toll-free hotline. Additionall~. information stored inside. One cop~ each vehicle will have ph8sical copies of this of the documents will be stored in a container affixed to the front passenger-side sun visor, and a second copiJ will be stored in a container affixed to the front driver-side sun visor. 3. How to Safely Remove the Waymo Vehicle From the Roadway A. If, for an \:I reason, one of Wa~Jmo's vehicles needs to be removed from the roadwa!:J, then we will arrange for a towing service. B. Alt.ernativel8, police can follow standard towing procedures with the vehicles, after disabling the Self-Driving Mode and turning the vehicles off, in accordance with the Wa8mo Emergenc8 Response Supplement, which is separatel8 being provided directl8 to state agencies and local police, firefighters, and other first responders. After disabling Self-Driving Mode, the vehicle ma8 be towed. If in manual mode, the vehicle can be towed like an~J conventional rear drive vehicle. Otherwise, the vehicle should be placed on a flatbed truck for removal. ©201!l Wo mo UG./\11 rights rescrvi.ld. Woymo l.ow Enforcement !ntno18 Woymo l.tG. All ri(~hts rcsmved. WQ[jrrJO low ~:;nfort:ement lnt\lmet1on Prot.oeoi • J Wa8mo's intended operational design domain will not initiall\:1 allow for driverless testing under the following conditions: Snow/icfd conditions Heav~ rain Flooded roadWO\:JS Offroad One-WOfd mountain roodwa\:ls During driverless testing, if On!:J of these conditions ore encountered, Wa\:lmo's vehicles are desi'gned to be capable of achi'eving a minimal risk condition without an\:! human intervention. Controlling the operating domain of its driverless vehicles is o part of Wafdmo's d!:Jnamio testing program. For the purpose of driverless testing, Wa!:JmO may choose to change domain constraints for some or all of its vehicles at various times. For example, driverless testing mal:J be limited to: Certain times of day Roadways of slower posted speed limits than 65 miles per hour Certain validated roadwa!:J features (including freewa!:J ramps, .· merge lanes, turn lanes, intersections, construction zones, roundabouts, cui de sacs, roundabouts, covered parking lots, restricted speed zones, and rail and light transit crossings) Non-inclement weather conditions ' DYNAMIC DRIVING TASK. Means all of tha raal-tlme functions reetl!eCurity lles.tPmd:i!?.e.li.· To help develop future securit8 best practices, Wa8mo has also joined the Auto-ISAC, an industq:toperated initiative created to enhance qJbersecurit!:J awareness and collaboration across the global automolive industru. On The Rood to Fully Self. Driving 18 Encrypt and Verify Channels of Communication Limit Communication Between Critical S!jstems Model and Prioritize Threats We complete a comprehensive review of all potential security access points to our selfwdriving system from both the interior and exterior of the physical vehicle, and take steps to limit the number and function of those access points. This begins b8 collaborating with our OEM partners at the onset to identif8 and mitigate vulnerabilities of the base vehicle. Our software and vehicle design processes take full account of known threats to ensure that our system and vehicle designs are protected against them. New software releases go through an extensive peer review and verification process. Our hazard analysis and risk assessment processes have been designed to identify and mitigate risks thot might affect safet!:J. including those related to c8bersecurit!:J. In our design, safet!:J~critical aspects of Waymo's vehicles-e.g. steering, braking, controllers-are isolated from outside communication. For example, both the safetttcritical computing that determines vehicle movements and the onboard 3D maps are shielded from, and inaccessible from, the vehicle's wireless connections and S!::JStems. We also consider the securit!::J of our wireless communication. Our vehicles do not rei!:J on a constant connection to operate safei!::J. '0fhile on the road, all communications (e.g., redundant cellular connections] between the vehicles and Wa!:JmO are encr!:Jpted, including those between Wa!:Jmo's operations support staff and our riders. Our vehicles can communicate with our operations center to gather more information about road conditions, while our vehicles maintain responsibilitl:l for the driving task at all times. These protections help prevent an8one with limited ph8sical access to our self·driving vehicles, whether passengers or malicious actors nearby, from impairing or altering their securit!:J. We have diverse mechanisms for noticing anomalous behavior and internal processes for analyzing those occurrences. Should we become aware of an indication that someone has attempted to impair our vehicle's securit!:J. Wa!:Jmo will trigger its compan~twide incident response procedure, which involves impact assessment, ---------cococc.nOitCca:lnment, recovertJ, ana remedialion. On Thu Rood to Fully Self·Driving 19 Waymo's technology undergoes extensive testing-on the road, in closed courses, and in simulationso that every part of our system is capable, reliable, and safe when operating within its design domain. Wat~rno's self-driving vehicles consist of three primari:J subsf:jstems that are individuallu and rigorousl8 tested: 1, The base vehicle, as certified by the OEM 2. Our in-house hardware, including sensors and computers 3. Our self-driving software that makes all the driving decisions Each of these subs8stems is then combined to form a full8 integrated selfdriving vehicle, which is then further tested and validated. Collectively testing the hardware and software ensures that our overall self-driving vehicle meets all the safetu requirements that we have set for our S!jstem. Wuymo Sufety Report 20 Base Vehicle Safety Wa!:Jmo's current generation self-driving vehicle is a modified version of the 2017 Chrusler Pacifica H8brid Minivan, into which we have integrated our self-driving S8stem. The modified 2017 Chrusler Pacifica Hubrid Minivans that Fiat Chr8sler Automobiles ["FCA") has sold to us have been certified bu the manufacturer as compliant with all applicable Federal Motor Vehicle Safetu Standards [FMVSS), which standards regulate the safetu performance requirements for motor vehicles or items of motor vehicle equipment in the U.S. Self-Driving Hardware Testing Through a technical collaboration between FCA and Wa8mo, we engineered and integrated Wa!:Jmo's self-driving S\:JStem, including our self-driving sensors and hardware, with the modified Chrusler Pacifica Hubrid Minivans provided bu FCA. To ensure that we have properlu integrated our self-driving sustem into the Chrusler Pacifica Hubrid Minivans that make up our fleet, Waumo has performed thousands of additional tests on top of those completed bu FCA. These tests are completed at our private test tracks, in our labs, and in simulation, and are used to evaluate each sa-fet\:1 function of the vehicle, ·from brakes and steering to phusical vehicle controls like locks, headlights, and doors. With these tests, we can ensure that the vehicle operates safei!::J in manual mode, self-driving mode with a test driver at the wheel, and fullu selfdriving mode without a person inside the vehicle. Overall, this testing seeks to ensure that our vehicle continues to function safeltj after the addition of our self-driving S8stem. On lhe Road to FuiiH Sel-l-Drilling 21 Self-Driving Software Testing like our hardware, our self-driving software is guided b8 our Safety by Design philosophy. We constant!~ and rigorousl8 test the individual components of the software-including perception, behavior prediction, and planner-~ as well as the software as a whole. Our technolog8 is constantl8 learning and improving. Each change of our software undergoes a rigorous release process. We update our software regular18 for different operational design domains. Each update is tested through a combination of simulation testing, closed course testing, and driving on public roadwa8s: Simulation Testing: In simulation, we rigorously test any changes or updates to our software before the8're deplo8ed in our fleet. We identif8 the most challenging situations our vehicles have encountered on public roads, and turn them into virtual scenarios for our self-driving software to practice in simulation. Closed-Course Testing: New software is pushed to a few vehicles first so that our most experienced drivers can test the new software on our private test track. We can use different releases of software for different vehicles so that we can test new or specific features within different operational design domains. Reai·World Driving: Once we confirm that our software is working as intended, we begin introducing the new software to our vehicles on public roads. We start small-our self-driving vehicles must show theu can safelu and consistentl!j travel a predetermined route-and then we push the software update to our entire fleet. The more miles we travel on public roads, the more opportunities to monitor and assess the performance of software. As we drive more road niiles, we continue to further refine our driving and update our software. This continual feedback loop allows us to build confidence that our software reacts and responds appropriatell:J in the operational design domain, enabling our vehicle to operate at SAE Level 4 safel8. On The nnod to Fullu Self-Driving Behavioral Competencies for Normal Driving A fully self-driving vehicle must be able to handle all the everyday driving tasks expected of human drivers within the same operational design domain. This means self··driving systems need to demonstrate they have the adequate skills-or "behavioral competencies"-required for the intended locations and conditions of operation. The U.S. Department of Transportation has recommended that Level 3, Level 4, and Level 5 self-driving vehicles should be able to demonstrate at least 28 core competencies adapted from research by California Partners for Advanced Transportation Technolog~ (PATH) at the Institute of Transportation Studies at UniversitH of California, BerkeleH. DOT also encourages companies "to consider all known behavioral competencies in the design, test, and validation" of a self-driving S8stem. WaHmo's safety program has expanded the 28 core competencies in both breadth and depth, for which we test thousands of scenario variationsranging in complexitH-ensuring that our SHstem can safeiH handle the challenges of real-world environments, In addition, we have identified further categories that expand upon the initial 28 core competencies. [17] (For a subset of WaHrno's behavioral competencies, see i\_p,Jlgndix.A.) For each competenc!:J, Wa!:Jmo's team creates a wide variet~ of individual tests to run on our closed course -facilitt~ and in simulation. For example, to test our abilitH to make unprotected left turns, we stage dozens of real-life situations and test to see if our vehicles respond appropriatei!:J. We include challenging variations of this common road maneuver, including using multiple lanes of oncoming tmffic, obstructing our vehicle's field of view with a large truck, or providing a short green traffic light to make the turn. For each of these scenarios we then use our simulator to create hundreds of different variations of the same encounter. With our virtual world testing, we can also create entirei!:J new scenarios of unprotected lefHmnd turns so we can test this skill further. As we expand our operational design domain, the number of core competencies may grow (for example, to drive in northern l),S, states ~ear-round, our StJStem must be· able to safel~ drive in snow) and the number of tests within each categor!:J ma!:J expand with more unique or complex scenmios. While this type of scenario testing can demonstrate our software's core driving skills, these competencies need to translate out into the real world. rhafs wh!:J this acts merel~ as a starting point: our validation then moves onto testing our vehicle, hardware, and software as an integmted fullu self~ driving vehicle on public roads, where it demonstrates these competencies daii!::J in real traffic situations. On The J·lood to Fui!u Se!f·Drivir.g Testing the Fully Integrated Self-Driving Vehicle After testing the base vehicle, the self-driving system, and the software individual!~. we then test the fully integrated self-driving vehicle. This includes closed-course collision avoidance testing, reliabilit~ and durabilit~ testing, and on-road testing with trained test drivers at the wheel. Testing on Public Roads Waymo has a comprehensive on-road testing program that has been improved and refined continuously over our eight-year historu. It's a critical step that allows us to validate the skills we have developed, uncover new challenging situations, and develop new capabilities. The safe\~ of our on-road testing program begins with highl8·trained drivers. Our test drivers undergo extensive classroom training, learning about the overall s~stem and how to monitor the vehicle safelu on public roads, including taking defensive driving courses. After this training, our drivers are responsible for monitoring the system and if needed, taking control of the vehicle while we test on public roads. Our on-road testing program drives tens of thouscmds of weekltJ miles that are used to evaluate our software. We monitor our S!:-JStems to ensure the!J demonstrate our behavioral competencies, and we look for situations where we can build on these competencies and enable smoother driving. Real-world testing provides a continuous feedback loop that lets us refine our StJStem continualltJ. Our engineers observe reaiRworld situations, make adjustments to the software to refine our driving, and then implement those changes. This iterative approach to testing and public-road validation helps us safeltJ scale our capabilities as we expand our operational design domain and the capabilities of our vehicles. On The Roud to Fuii!J Self·f>rlving '6 WA CA g AZ ~iJ €; c;: t~ ;) .,-;; " "' .;_:; e G "P • i;ii 'i·Y ' ·:;? ::;':; G ·;,") f? '" ffl; - €.;.- r;,'f; "~" '.:-· -- ~ -;:! :;:;1 .,, s· q -::~ - ',J ·--~ """' l;: .:;-; ~-;; t·, <:'i £"; ~..; '-~;,;;.- ::;f_• Over 3.5 Million Miles of Real-World Experience Testing Crash Avoidance Capabilities In addition to testing core behavioral competencies, our engineers also conduct crash avoidance testing across a variet~ of scenarios. (To view a subset of Wat~mo's crash avoidance test scenarios, see Appendix B.) Wat~mo has completed thousands of crash avoidance tests at our private test track. Each of these individual tests recreates a distinct driving scenario and allows us to analyze our vehicles' response. We then use our simulator to test these scenarios further and improve our overall software capabilities. We draw from a variet!:J of sources to learn which collisions to test against. Thet.J include our own analtJsis of sources such as NHTSA's fatal crash data base, and use of our extensive experience operating self~driving vehicles to expand on NHTSA's 37 pre~crash scenarios. We also test situations in which other road users c.reate potentialltJ dangerous situations, such as vehicles suddenltJ pulling out of driveways, large vehicles cutting across target lanes, motorctJclists weaving through traffic, and pedestrians ja!:Jwalking. In 2015, NHTSA published data showing the distribution oft he most common pre~crash scenarios. For example, just four crash categories accounted for 84% of all crashes: rear end crashes, vehicles turning or crossing at an intersection, vehicles running off the edge of the road, and vehicles changing lanes. Therefore, avoiding or mitigating those kinds of crashes is an important goal for our testing program. [18] Crash avoid a nco testing at Wawno's clm:ed cm;rsH testing On The flood to Fuii!-J Seli-Driving facilit~J, Castle. 20 Hardware Reliability and Durability Testing Self-driving vehicles, like their conventional counterparts, must operate reliablu. That means the vehicle and each of its individual components must function under extreme environmental conditions and over the lifetime of the vehicle. Waumo engineers design unique stress tests. Using our knowledge of the phusios of failure to accelerate environmental stresses on our vehicle· and its individual components, we compress tJBars of real-world use into da!:JS and weeks of testing. We blast our components with ultraviolet radiation, bombard them with powerful water jets, dunk them into nearl!j freezing vats of water; corrode them in chambers full of salt~ mist, shake and shock them with powerful vibrations, and heat and freeze them for weeks at a time in temperature and humid it!:) chambers. We anal~ze an~ failures and make design improvements to increase the reliabilit~ of our components. We monitor the health of each sensor, and the vehicle itself, so we can identif~ and fix potential failures before the!:J occur. Ou The [~QI)d l,(l Full!:) Sei'I'··Driving 29 Our vehicles are designed to drive themselves, so our user interface focuses on passengers, not drivers. That's why we've developed specific in-car features and user interfaces thot help our passengers understand what our vehicles are doing on the rood and let them do things like set a destination, ask the vehicle to pull over, and get in touch with Wa!:-Jmo support staff as needed. We also understand the transportotion challenges that exist todatJ, especially around accessibilit!:J, and we are working to develop solutions that work for riders of all obilities. In addition to creating a safe and intuitive everyda!:l ride for our passengers, Waymo has also developed procedures in case of emergenc!:J. For exomple, not oni!:J are our vehicles designed to detect collisions and respond appropriate18 to emergenc8 vehicles on the road, but we have also conducted trainings with law enforcement and first responders who rna8 come into contact with our vehicles. Finall8, the potential of self-driving cars will onl8 be realized bu growing public awareness and acceptance of this technolog8. In October 2017, Wa8mo helped to launch Lot's Talk Self-Driving (letstalkselfdrivin~J, the world's first public education campaign about full8 self-driving vehicles. Working in partnership with national and local safet8, mobilit8, and seniors groups, the initiative hopes to engage and educate the public about how this technolog8 works and the enormous benefits self-driving technolog8 could unlock. On The Rood to Fullu Self.. [)riving 30 Rider Experience WatJmo's user experience is guided by four main principles: give passengers the information they need for a seamless trip; help passengers anticipate what's next; proactively-communicate the vehicle's response to events on the road; and help passengers engage safel~ with the vehicle. Audio and visual information pr·ovided to passenger·s helps them know what to expect, reminds them of safettl features such as seat belts, and permits them to communicate with Wat~mo's rider support personnel. We also want our passengers to be aware of what the vehicle is perceiving, and why it is taking specific actions. Each vehicle also provides occupants with useful visual and audio information throughout the trip, to help them understand what the vehicle and other road users around it are doing. In Waymo's self~driving minivans, the in~vehicle screens are used to provide visual ride information, such as destination, current speed, and the route the vehicle intends to take. An audio S!:JStern provides audible notifications and cues to all riders. In the event of a safetwcritical event, the screens and audio s!1stem are designed to provide the occupant with specific visual and audio cues depending on the nature of the event. We've designed multiple wa~s for our riders to interact with our vehicle, whether it's through the pressing of ph~sical buttons, a mobile app, orb~ speaking with a Wa~mo rider support specialist. On Tlw Rood to Fuii!J Sel'f..Orivir.g 31 Accessibility: Unlocking Opportunities for Those Who Cannot Drive Today We believe our technolog8 holds the potential to improve safet8 and mobilit8 for people around the world. From the start, Wa8mo has been listening to and working with the disabilit!:J communit!:j. We continue to learn about the unique needs of different riders, and what we learn will inform n0w features that will make the experience accessible to people who have historicall8 had to rel8 on others to get around. We also know we can't reach our goals alone. Wa!:Jmo is committed to working with our partners to identiftJ vehicle platforms and solutions that can serve a broader set of individuals. On The 11oad to Fullu Self·Driving 32 Emergencies and Interacting With Law Enforcement and First Responders Our self-driving vehicles are designed to interact with law enforcement and first responders safei!:J on road. Using our suite of custom~built sensors, including an audio detection S!:JStem, our software can identif!J a nearb~J fire truck, detect its flashing lights, and hear sirens up to hundreds of feet away. Our audio sensors are designed to discern the direction sirens are likel8 coming from, improving our vehicles' abilit8 to respond in both a safe and timei!:J manner. Once an emergencu vehicle is detected, our vehicle can respond b8 8ielding, pulling over to the side of the rood, or coming to a complete stop. Wa!:Jmo also briefs local authorities in evertJ citu in which we test, and offers a line of communication for further engagement. In some cities, Wa!jmO has also conducted on-site training to help police and other ernergenctJ workers identify and access our vehicle in ernergenc!j situations. We plan to continue conducting these on~site trainings, while expanding the scope of the training program as our vehicles become more capable and our operational design domain expands. On The fior;d to f:ullu Self-Driving For more than eight ~:~ears, Wa~:~mo has focused on one thing: bringing fuii!:J self-driving technolog!:j to the world. We are committed to Safety By Design, and we have built a culture that puts safet~:~, and open communication about safet!:j, at its core. All of us at Wa!:Jmo are committed to the goal of making it safe and eas!:l for people and things to move around. This report summarizes our efforts to ensure the safe deployment of fully self-driving vehicles that use Waymo technology. We are excited about the potential this technology holds to improve road safety and provide new mobility options for the world. For further information about Wa!:Jmo's self-driving technology, please visit www.wgy_lllO.§;Offi, On The Road to hlii!J Self··Driving 34 Wa8mo tests our vehicles comprehensivel8 to ensure thot the8 are capable of operating safeltj in reasonabltJ foreseeable scenarios that could present a safettl hazard, The following l8pes of scenarios are illustrative of the breadth of our testing program and are designed to ensure our vehicles have: ·1) basic behavioral competencies and 2) the abilitu to avoid or mitigate crashes in common crash scenarios. On The flood to Fully Self-Driving 35 Appendix A. Basic Behavioral Competency Testing We believe that our full8 self-driving vehicles should be able to successfull8 demonstrate competenc8 in a variettJ of reasonabi!:J foreseeable traffic situations that are within the vehicle's operational design domain. Our StJStem can recognize and stal:J within its des'1gn domain, and the set of competencies expands or shrinks in accordance with the scope of each operational design domain. For each behavioral competencl:J shown in the table below, we test a wide range of scenarios with variations in factors such as road configuration, the speed of our vehicle or other vehicles, and lighting conditions. ·. Set of Behuvloral Compe:l:enelet R~ommended by·.NHT$A . .. 1 Detect and Respond to Speed Limit Changes and Speed Advisories 2 Perform High·Speed Merge [e.g., Freewa~) ...... _ ....._-·-·-·· - " " " " " - - """""""""""""""'""'"""""""""'-"'"-"""""-"""""""'-""""--"·--------···----· 3 Perform low-Speed Merge 4 Move Out of the Travel Lane and Park (e.g., to the Shoulder for Minimal Risk] 5 Detect and Respond to Encroaching Oncoming Vehicles 6 Detect Passing and No Passing Zones and Perform Passing Maneuvers 7 Perform Cor Following (Including Stop and Go] ""'"'-""' 1-·. ---..--.... -8 . ···- Detect and Respond to Stopped Vehicles -··--- 9 _,,,,. __ 10 Detect and Respond to Lane Changes Detect and Respond to Static Obstacles in the Path of the Vehicle ---·-· 11 Detect Traffic Signals and Stop/Yield Signs 12 Respond to Traffic Signals and Stop/Yield Signs --··--· 13 Navigate Intersections and Per-form Turns .......... 14 Navigate Roundabouts 16 Navigate a Parking Lot and Locate Spaces -16 Detect and Respond to Access Restrictions (One-Way, No Turn, Ramps, etc.] 17 Detect and Respond to Work Zones and People Directing Traffic in Unplanned or Planned Events 18 Make Appropriate Right·of-Way Decisions ·-~""'"" 19 Follow local and State Driving laws ·--"""-'" On The Rood to Fuii!:J Self-Driving 36 Follow Police/First Responder Controlling Traffic (Overriding or Acting as Traffic Control Device) Follow Construction Zone Workers Controlling Traffic Patterns (Slow/Stop Sign Holders] Respond to Citizens Directing Traffic After a Crash Detect and Respond to Temporary Traffic Control Devices Detect and Respond to Emergency Vehicles for Law Enforcement, EMT, Fire, and Other Emargencl:J Vehicles at Intersections, Junctions, and Other Traffic Controlled Situations Yield to Pedestrians and Bic1:1clists at Intersections and Crosswalks Provide Safe Distance From Vehicles, Pedestrians, Bicyclists on Side of the Road Detect/Respond to Detours and/or Other Temporar1:1 Changes in Traffic Patterns . 29 . . Examples of Additional Behavfor!ll .._ Tested.by Waymo ____ ________ Moving to a Minimum Risk Condition When Exiting the Travel Lone is Not Possible .... ,_.,, ... _...,,, """""""-"-""""'"""""""""""""--··-· ... ,.. ---· _._,. - 30 Perform Lane Changes --··--""""' """'"""""""""" ___ """""'"'"""'----"-"""""'-"'" Detect and Respond to Lead Vehicle 32 Detect and Respond to a Merging Vehicle ·---· ~ ·--·. ··--. --··~-~~·---Detect and Respond to Pedestrians in Road (Not Walking Through Intersection or Crosswalk) -·-"'-"'-"'"""'" """'~-· 33 _...,. ...- ... r---3'+ _,.. r-------------------35 Detect and Respond to Animals __ -·--·- ·-·-··---·-· ____ ,. ... -------- ---- - -·~···-···-----·--·- "·"" Provide Safe Distance from Bicl:Jclists Traveling on Road (With or Without Bike Lane) - ,,-~. ·--'"""' ·-...·------ 31 ...,..... .•. -·--------- , ____ '"W"~-' ,. " " ~ " - • • m • ' • - ' " " " ' Motorct~clists " Detect and Respond to -- " 36 m-•-•w~" -··-·--~-•-•c••-m' ________ •·--n-·~-·•-w'""''""'" 37 Detect and Respond to School Buses 38 Navigate Around Unexpected Road Closures (e.g. Lane, Intersection, otc.) 39 Navigate Railroad Crossings · - - - ·~•- mw-wmm•-•~ ..···------ --··-···----·····- ~~· - -·-·'""""""" m-~"'"" 40 Make Appropriate Reversing Maneuvers 41 Detect and Respond to Vehicle Control Loss (e.g. reduced road friction) 42 Detect and Respond to Conditions Involving Vehicle, S!:jstem, or Component-Level Failures or Faults (e.g. power failure, sensing failure, sensing obstruction, computing failure, Fault handling or response) -----··- - ----- .... -~-·-·-·---- - - -·-· ·--- ··-·· .. 43 --·-···- -"--.. -m-•-•m- .. ··----- ---- ------·~---~- Detect and Respond to Unanticipated Weather or Lighting Conditions Outside of Vehicle's Capability [e.g. rainstorm) --- -----·--·-"""'"-'"'~ -w·-·-~--•w~~ 44 Detect and Respond to Unanticipated Lighting Conditions (e.g. power outages) 45 Detect and Respond to Non-Collision Safet1:1 Situations (e.g. vehicle doors ajar) 46 -47 ··-·- - .. ~-- .. --- Detect and Respond to Vehicles Parking in the Roadwa\:1 .... ~····-· -- --•~••.,~m~" Detect and Respond to Faded or Missing Roadwal:j Markings or Signage ,_.., ... ~.~- --- --------- ··~-~-·- ... ... -~ --------------- "" . ···-- =··· ------·~·--- --- ~----·· ------- -~~--··-- -- - _,_, __ -··· 37 Appendix B. Avoidance or Mitigation of Common Crash Scenarios Certain t\:jpes of crashes account for a substantia! percentage of all crashes. Avoiding or mitigating those kinds of crashes, therefore, is an important goal for our vehicle development program. In late 2015, NHTSA published data showing the distribution of pre-crash scenarios. [19] Four scenarios accounted for the vast majority of crashes: 29 percent of the vehicles were involved in rear-end crashes 24 percent of the vehicles were turning or crossing at intersections just prior to the crashes 19 percent of the vehicles ran off the edge of the road 12 percent involved vehicles changing lanes Therefore, these scenarios figure prominentltj in the evaluation of our vehicles. The table below illustrates just a few of the test scenarios we emplotj to determine our vehicle's abilittJ to avoid or mitigate crashes in these all-important situations, as well as in other crash situations. ·----Example Test Scenario Crash Avoidance Category ·Fulfg self~rlv'rn-g-velitof.e Ct'fiip>rCY(;f()ha$ 'hZJ~dd ve·hid_e irove-tlng at lower aonstanl speerd -Fu!l_H seff..drTvfng 'vehicle: ap-pt_o-tti'Ohe$lt:iad vehicle· trovelfhg ttt slower Ef?~S-d _unQ .tnH_latrri~f${rprttif br~ktng Rear-end .. · ·· . D\irn6rislfo~o i:>bliii:!J ro'ol'old or 11\l!lgt~t•"Cn'lsnet wiiK l~Ef• c-ut~intJ _l_r'!t(;j !One (Yf):YUJlhY@ (5Ut bf__ drtv.ewo:gJ ap]>Fo for the timel!j identification of hazards, and initiation of those actions necessar!:J to prevent or mitigate hazards within the system. On The Road to Ful!u ;'ieiH)rfvino ,,, [1] "Critical Reasons for Crashes Investigated in the National Motor Vehicle Crash Causation Surve8." National Highwa8 Traffic Safet8 Administration, Februar8 2015. https://crashstot,.nhtsq.dot.gov/Api/ Public/ViewPubliegtion/812115 [2] "Global Status Report on Road Safet8 2015." World Health Organization, 2015 . .bitr2i/.YL"YW.who.int/ violence injur\J prevention/road sgfflt\J Bt.otus/2015/en/ [3] "2016 Fatal Motor Vehicle Crashes: Overview." Nationalllighwa8 Traffic Safet8 Administration, October 2017. https:/b.rn!ih~!ill§,nhtsp.dot.goytl\j2i/Public/ViewPublication/812456; "Quick Facts 2015." National Highwa8 Traffic Safet8 Administration, Ma8 2017 (updated). https://crashstats.nhtsa.dot.qov/ P.!P-i/l'.i!Q! ic/Vi ewPu blicatj oJ:J.L!lm.'±Jl. [1+] "The Economic and Societal Impact Of Motor Vehicle Crashes, 201 0." National Highwa8 Traffic Safot8 Administration, Ma8 2014, DOT HS 812 013. hJ.W,s:Uwww-nrd.nhtsa.dot.gov/Pubs/812013.pdf [5] "The Economic and Societal Impact Of Motor Vehicle Crashes, 201 0." National Highwa8 Traffic Safetu Administration, Ma8 2015 (revised). httr;l§i/crashstats.nhtsg.dot.gQ'/il.~.iLPublic/ViewPublication/812!ll.:l. [6] ibid. [7] Schrank, D., Eisele, B., Lomax, T., and Bak, J. "2015 Urban Mobilit8 Scorecard." The Texas AGM Transportation Institute and INRIX, August 2015. h!1!l§:L/~.!g![G.•i!i.!gmy,§'t~!/iti.tamll.egy/ggcum9lli!/ mob iIity.:!Qa reggr!J- 2Q1Il..J~.!l1. [8] "Quieter Cars and the Safet8 Of Blind Pedestrians: Phase 1." National Highwa8 Traffic Safet8 Administration, April 20 10. hltfl~;L/~,n hl!la.gov /Q.OT/N HTSA/NVsLcrash% 2JlAYilid9..0.Q§/Iech nioi!!3:'9ZQ £ybJkgli9Ld2QJ..QLal1304rcy..fli:J.! [9] Rosenbloom, Sandra. "The Mobilit8 Needs of Older Americans: Implications for Transportation Reauthorization." The Brookings Institution, Jul8 2003 ..h!iJ;lldL'!Y.!:!!,!l.9.flllll~ecJ. [13] "SAE J30 16. Toxonom8 and Definitions for Terms Related to Driving Automation S8stems lor On-lload Motor Vehicles." SAE International, September 2016. [1 It] "Federal Automated Vehicles Polic8." National Highwa8 Traffic Safet8 Administration, September 2016. (See Safet8 Assessment notes on page 15.) ~/.L;yww,tran~!li!lJl,gQ'/il.Y.L f!lQllLal-automat!I!J-vehiok;s-pglicu-l&Jltc.mb~r-2019. (15] As NHTSA has noted: "A minimal risk condition will var8 according to the t8pe and extent of a given failure, but mau include automaticall8 bringing the vehicle to a safe stop, preferabl8 outside of an active lane of traffic." (See Automated Driving S8stems 2.0 on page 8.) On '['he Rood to Fulli:J Solf..l')riving lt2 [16] Crashes are reported consistent with state law and we cooperate with law enforcement under established legal process. [17] "Input to NHTSA's Development of Guidelines for the Safe Deplo8ment and Operation Of Automated Vehicle Safet8 Technologies." Google, Inc., Ma8 2016. hl1f)J&;liilliY!l.,I)Q.QQ!o.com/ .fililLd/OBuq-WV>!3Y4HEcWVvVjc3TXEwOEE/viow?usp=sharing [1 B] "New Car Assessment Program (NCAP), 80 Fed Reg 78522 at 78552, December 16, 2015) https://www.fedorqlregistqt;g.Qv/documonts/40 15/12/16/20'15-31323/now·car-assossment::>J.rogram [19] Our test scenarios are derived from multiple sources, including: Najm, W. G., Smith, J. D., and Yanagisawa, M. "DOT HS 810 767: Pre-Crash Scenario Twolog8 for Crash Avoidance Research." National Highwa8 Traffic Safet8 Administration, April2007. https://www.nhtsa.>Jov/sites/nhtsa.dot.gov/fi!es/procrash sconmio t~polog~-final pdf version 5-2-0?,gdf Data from the NIITSA's Fatalit8 Anal8sis Reporting S8stem (FARS) database https://www.nhtso.gllYL J:lll!Jl.arillJodJ:lj;gftgmlli!J:ll!l.gjy§i.§:f!l$!Wl!;i:2lllillli!l:fan;, and hazardous situations Wa8mo has encounterod during our eight !:Jears of driving experience. On Thu Rood to Fully Self-Drivin(~ J. Copy of Waymo's Corporate Information Filed with the Secretary of State Application content enclosed on the following page. 17-314799 LLC·12 Sl!leretary of State Statement of lnfllrmatlon (Limited Liability Cllmpeny) FILED Seerell!y of Slate IMPORTANT- R•od lm!llw:lkm• _.,. oomllf! pogo $1.!10; •ollll otllillilmll!IIJ)Ilgo $1).50; C.rtlft- Fe • ~GJJO pluo oepy- li'WIVI!:WAl-CimlpWU; ftemtt Q 41~td Gb i»lly; MUllt htt!lu;fe &gMI'J:r. filii m:un:e Ulll(j CA!Ifmlla alttlru. ruidrtf;tt>,. Aum<'--::::::';<_,~p~;i;.d'~' ~{ilatJd ll'lll,1llll~!!ll~ - • f:kitnJtWltMUP,O. ilml ~-- . J"''"- ---··-J~~··-: rutv!no~) -,-,.w-·=..-·-'M ""-'--"' CORJJOM"'iOU- Cmnpie'ltll\w;m 13(1 elllf)'. Olii)'frn;kJtfa the nmno Of 1tm msl5tmrui agent C~e. ~~~=-:e=~:"~;':~"':'::;:;;:;;;~: CSC·LII~ rnmrporati::::-1}\)qt/qO) ~ ~~~ lrttil'ft Addmsili ~JSril'l ortltlMJflti:lY a~ld lhe.l'l'lllllinomt:Jmq, Tlilsfu:ru;~ wlil booonitipubllu~flled. ~ N"""" Compllny: m~llili~•~.J~::-,------ (Optional} fW ilMMilll'OOai!OO fi'um-ltm SM111buy at _S'tlltu ~ b !hit dalltU!tOOt, or 1f plimhn&Jn ~ OlfiV et iha fl&MI ®OOiflj!ifl t attltw 1tm n&tUO 1»1 .a r !NmtJ