Keynote (Google I/O ’18)

♪ (electronic pop) ♪ (applause) Good morning. (cheering) Welcome to Google I/O. It’s a beautiful day;
I think warmer than last year. I hope you’re all enjoying it.
Thank you for joining us. I think we have
over 7,000 people here today. As well as many, many people– we’re live streaming this
to many locations around the world. So, thank you all for joining us today.
We have a lot to cover. But, before we get started, I had one important business
which I wanted to get over with. Towards the end of last year,
it came to my attention that we had a major bug
in one of our core products. – It turns out…
– (laughter) …we got the cheese wrong
in our burger emoji. Anyway, we went hard to work. I never knew so many people
cared about where the cheese is. – (laughter)
– We fixed it. You know, the irony of the whole thing
is I’m a vegetarian in the first place. (laughter and applause) So, we fixed it–
hopefully we got the cheese right, but as we were working on this,
this came to my attention. (laughter) I don’t even want to tell you
the explanation the team gave me as to why the foam
is floating above the beer. (laughter) …but we restored
the natural laws of physics. (laughter) (cheering) So, all is well.
We can get back to business. We can talk about all the progress
since last year’s I/O. I’m sure all of you would agree it’s been an extraordinary year
on many fronts. I’m sure you’ve all felt it. We’re at an important inflection point
in computing. And it’s exciting
to be driving technology forward. And it’s made us even more reflective
about our responsibilities. Expectations for technology vary greatly, depending on where you are in the world, or what opportunities are available to you. For someone like me,
who grew up without a phone, I can distinctly remember how gaining access to technology
can make a difference in your life. And we see this in the work we do
around the world. You see it when someone gets access
to a smartphone for the first time. And you can feel it in the huge demand
for digital skills we see. That’s why we’ve been so focused
on bringing digital skills to communities around the world. So far, we have trained
over 25 million people and we expect that number
to rise over 60 million in the next five years. It’s clear technology can be
a positive force. But it’s equally clear
that we just can’t be wide-eyed about the innovations technology creates. There are very real
and important questions being raised about the impact of these advances and the role they’ll play in our lives. So, we know the path ahead
needs to be navigated carefully and deliberately. And we feel a deep sense of responsibility
to get this right. That’s the spirit with which
we’re approaching our core mission– to make information more useful, accessible, and beneficial to society. I’ve always felt
that we were fortunate as a company to have a timeless mission that feels as relevant today
as when we started. We’re excited about how
we’re going to approach our mission with renewed vigor, thanks to the progress we see in AI. AI is enabling for us to do this in new ways, solving problems for our users
around the world. Last year, at Google I/O,
we announced Google AI. It’s a collection of our teams and efforts to bring the benefits of AI to everyone. And we want this to work globally, so we are opening AI centers
around the world. AI is going to impact many, many fields. I want to give you
a couple of examples today. Healthcare is one of the most
important fields AI is going to transform. Last year we announced our work
on diabetic retinopathy. This is a leading cause of blindness, and we used deep learning
to help doctors diagnose it earlier. And we’ve been
running field trials since then at Aravind and Sankara hospitals in India, and the field trials are going really well. We are bringing expert diagnosis to places where trained doctors are scarce. It turned out, using the same retinal scans, there were things which humans
quite didn’t know to look for, but our AI systems offered more insights. Your same eye scan, it turns out, holds information with which we can predict the five-year risk of you having an adverse
cardiovascular event– heart attack or strokes. So, to me, the interesting thing is that, more than what doctors
could find in these eye scans, the machine learning systems
offered newer insights. This could be the basis
for a new, non-invasive way to detect cardiovascular risk. And we’re working–
we just published the research– and we’re going to be working
to bring this to field trials with our partners. Another area where AI can help is to actually help doctors
predict medical events. It turns out, doctors have a lot
of difficult decisions to make, and for them, getting advanced notice– say, 24-48 hours before
a patient is likely to get very sick– has a tremendous difference in the outcome. And so, we put
our machine learning systems to work. We’ve been working with our partners using de-identified medical records. And it turns out if you go and analyze
over 100,000 data points per patient– more than any single doctor could analyze– we can actually quantitatively predict the chance of readmission, 24-48 hours earlier than traditional methods. It gives doctors more time to act. We are publishing our paper
on this later today and we’re looking forward to partnering
with hospitals and medical institutions. Another area where AI can help
is accessibility. You know, we can make day-to-day use cases
much easier for people. Let’s take a common use case. You come back home at night
and you turn your TV on. It’s not that uncommon
to see two or more people passionately talking over each other. Imagine if you’re hearing impaired and you’re relying on closed captioning
to understand what’s going on. This is how it looks to you. (two men talking over each other) As you can see, it’s gibberish–
you can’t make sense of what’s going on. So, we have machine learning technology
called looking to listen. It not only looks for audio cues, but combines it with visual cues to clearly disambiguate the two voices. Let’s see how that can work,
maybe, in YouTube. (man on right)
He’s not on a Danny Ainge level. But, he’s above a Colangelo level. In other words,
he understands enough to… (man on left) You said
it was alright to lose on purpose. You said it’s alright to lose on purpose, and advertise that to the fans. It’s perfectly okay.
You said it’s okay! We have nothing else to talk about! (Sundar) We have a lot to talk about.
(chuckles) (laughter) (cheering) But you can see
how we can put technology to work to make an important
day-to-day use case profoundly better. The great thing about technology
is it’s constantly evolving. In fact, we can even apply machine learning to a 200-year old technology– Morse code– and make an impact
on someone’s quality of life. Let’s take a look. ♪ (music) ♪
(beeping) (computer’s voice)
Hi, I am Tania. This is my voice. I use Morse code by putting dots and dashes with switches mounted near my head. As a very young child, I used a communication word board. I used a head stick to point to the words. It was very attractive, to say the least. Once Morse code
was incorporated into my life, it was a feeling
of pure liberation and freedom. (boy) See you later.
Love you. I think that is why
I like sky diving so much. It is the same kind of feeling. Through sky diving,
I met Ken, the love of my life, and partner in crime. It’s always been very, very difficult just to find Morse code devices, to try Morse code. (Tania) This is why I had to create my own. With the help from Ken, I have a voice, and more independence in my daily life. But most people don’t have Ken. It is our hope that we can collaborate
with the Gboard team to help people who want to tap into
the freedom of using Morse code. (woman) Gboard is the Google keyboard. What we have discovered, working on Gboard, is that there are entire pockets
of populations in the world– and when I say “pockets”
it’s like tens of millions of people– who have never had access to a keyboard
that works in their own language. With Tania, we’ve built support
in Gboard for Morse code. So, it’s an input modality that allows you
to type in Morse code and get text out with predictions, suggestions. I think it’s a beautiful example
of where machine learning can really assist someone
in a way that a normal keyboard, without artificial intelligence, wouldn’t be able to. (Tania) I am very excited
to continue on this journey. Many, many people will benefit from this and that thrills me to no end. ♪ (music) ♪ (applause) It’s a very inspiring story. We’re very, very excited
to have Tania and Ken join us today. (cheering) Tania and Ken are actually developers. They really worked with our team to harness the power
of actually predictive suggestions in Gboard, in the context of Morse code. I’m really excited
that Gboard with Morse code is available in beta later today. It’s great to reinvent products with AI. Gboard is actually a great example of it. Every single day, we offer users– and users choose–
over 8 billion auto correction each and every day. Another example of one of our core products which we are redesigning with AI is Gmail. We just had a new, fresher look for Gmail– a recent redesign. I hope you’re all enjoying using it. We’re bringing another feature to Gmail. We call it Smart Compose. So, as the name suggests, we use machine learning
to start suggesting phrases for you as you type. All you need to do is to hit Tab
and keep auto-completing. (applause) In this case, it understands
the subject is “Taco Tuesday.” It suggests chips, salsa, guacamole. It takes care
of mundane things like addresses so you don’t need to worry about it– you can actually focus
on what you want to type. I’ve been loving using it. I’ve been sending
a lot more emails to the company… – …not sure what the company thinks of it.
– (laughter) But it’s been great. We are rolling out Smart Compose
to all our users this month and hope you enjoy using it as well. (applause) Another product,
which we built from the ground up using AI is Google Photos. Works amazingly well, and it scales. If you click on one of these photos, what we call the “photo viewer experience” where you’re looking at one photo at a time, so that you understand the scale. Every single day there are
over 5 billion photos viewed by our users, each and every day. So, we want to use the AI
to help in those moments. We are bringing a new feature
called Suggested Actions– essentially suggesting small actions right in context for you to act on. Say, for example, you went to a wedding and you’re looking through those pictures. We understand your friend, Lisa,
is in the picture, and we offer to the share
the three photos with Lisa, and with one click
those photos can be sent to her. So, the anxiety where everyone is trying
to get the picture on their phone, I think we can make that better. Say, for example,
if the photo– in the same wedding– if the photos are underexposed, our AI systems offer a suggestion to fix the brightness right there, one tap, and we can fix the brightness for you. Or, if you took a picture of a document
which you want to save for later, we can recognize,
convert the document to PDF, – and make it…
– (cheering) …make it much easier for you to use later. We want to make
all these simple cases delightful. By the way,
AI can also deliver unexpected moments. So, for example,
if you have this cute picture of your kid, we can make it better– we can drop the background color,
pop the color, and make the kid even cuter. (cheering) Or, if you happen to have
a very special memory, something in black and white–
maybe of your mother and grandmother– we can recreate that moment in color and make that moment
even more real and special. (cheering) All these features are going to be
rolling out to Google Photos users in the next couple of months. The reason we are able to do this is because, for a while,
we have been investing in the scale
of our computational architecture. This is why last year we talked
about our Tensor Processing Units. These are special purpose
machine learning chips. These are driving all the product
improvements you’re seeing today. And we have made it available
to our Cloud customers. Since the last year, we’ve been hard at work, and today, I’m excited to announce
our next generation TPU 3.0. (cheering) These chips are so powerful
that for the first time we’ve had to introduce
liquid cooling in our data centers. (cheering) And we put these chips
in the form of giant pods. Each of these pods is now 8x
more powerful than last year– it’s well over 100 pedaflops. And this is what allows us
to develop better models, larger models, more accurate models, and helps us tackle even bigger problems. And one of the biggest problems
we’re tackling with AI is the Google Assistant. Our vision for the perfect Assistant is that it’s naturally conversational, it’s there when you need it so that you can get things done
in the real world. And we are working to make it even better. We want the Assistant to be something
that’s natural and comfortable to talk to. And to do that, we need to start with the foundation
of the Google Assistant– the voice. Today, that’s how most users
interact with the Assistant. Our current voice is code-named “Holly.” She was a real person.
She spent months in our studio. And then we stitched
those recordings together to create Voice. But 18 months ago, we announced a breakthrough
from our DeepMind team called WaveNet. Unlike the current systems, WaveNet actually models
the underlying raw audio to create a more natural voice. It’s closer to how humans speak– the pitch, the pace, even all the pauses, that convey meaning. We want to get all of that right. So, we’ve worked hard with WaveNet, and we are adding, as of today, six new voices to the Google Assistant. Let’s have them say hello. (voice #1) Good morning, everyone. (voice #2) I’m your Google Assistant. (voice #3) Welcome
to Shoreline Amphitheatre. (voice #4)
We hope you’ll enjoy Google I/O. (voice #5) Back to you, Sundar. (applause) Our goal is, one day, to get the right accents, languages,
and dialects right, globally. WaveNet can make this much easier. With this technology, we started wondering
who we could get into the studio with an amazing voice. Take a look. Couscous: A type of North African
semolina and granules made from crushed durum wheat. (trilling) I want a puppy with sweet eyes
and a fluffy tail who likes my haikus. Don’t we all? (singing) ♪ Happy birthday,
to the person whose birthday it is… Happy birthday… …to you ♪ John Legend… He would probably tell you
he don’t want to brag but he’ll be the best assistant
you ever had. (man) Can you tell me where you live? You can find me on all kinds of devices– phones, Google Homes, and, if I’m lucky… …in your heart. (laughter and applause) That’s right– John Legend’s voice
is coming to the Assistant. Clearly, he didn’t
spend all the time in the studio answering every possible question
that you could ask. But WaveNet allowed us
to shorten the studio time, and the model can actually
capture the richness of his voice. His voice will be coming later this year
in certain contexts so that you can get responses like this: (John Legend’s voice)
Good morning, Sundar. Right now, in Mountain View,
it’s 65 with clear skies. Today, it’s predicted
to be 75 degrees and sunny. At 10 a.m. you have an event
called Google I/O Keynote. – Then, at 1 p.m. you have margaritas.
– (laughter) Have a wonderful day. I’m looking forward to 1 p.m. (laughter) So, John’s voice is coming later this year. I’m really excited we can
drive advances like this with AI. We are doing a lot more
with the Google Assistant. And, to talk to you a little more about it, let me invite Scott onto the stage. Hey Google. Call Maddie. (Assistant) Okay, dialing now. Hey Google. Book a table for four. (Assistant) Sounds good. Hey Google. Call my brother. Hey Google. Call my brother. Text Carol. Can you text Carol for me, too? Hey Google. Who just texted me? – Yo Google.
– (man) Cut! Kevin, that was great. But we haven’t made “Yo Google” work yet, so you have to say “Hey”. (together) Hey Google. – (calling) Hey Google.
– Play some Sia. (lip trilling) Hey Google, play the next episode. Play The Crown on Netflix. All Channing Tatum movies. (Assistant) Okay. – Yo Google.
– (man) Cut! That was great. Can we just get one
where you say, “Hey Google”? Hey Google. Find my phone. (Assistant) Finding now. Whoa! – Hey Google.
– (whispering) Hey Google. (man yelling) Hey Google! Yo Google. Lock the front door. (man) Cut! (man) Okay.
Let’s just go with Yo Google then. I’m sure the engineers
would love to update… everything. Yo. ♪ (music) ♪ (Assistant) Hi, what can I do for you? ♪ (music) ♪ (cheering) Two years ago we announced the Google Assistant
right here at I/O. Today, the Assistant is available
on over 500 million devices, including phones, speakers, headphones, TVs, watches, and more. It’s available in cars
for more than 40 auto brands, and it works with over
5,000 connected home devices, from dishwashers to doorbells. People around the world
are using it every single day. For example, we launched the Assistant
in India last year, and the response has been incredible. Daily usage there has tripled
since the beginning of the year. By the end of this year, the Assistant will support 30 languages and be available in 80 countries. So, we’ve made great progress. But we’re just getting started. Today, we’re going to share with you
some important ways that the Assistant is becoming
more naturally conversational and visually assistive, in order to help you do more
and get time back. Now, as you heard from Sundar, new voices that you can choose from
to make the Google Assistant your own are an important aspect of making the conversation
with your Assistant more natural. But to be a great conversation partner, the Assistant needs to deeply understand
the social dynamics of conversation. For example, let’s be honest, it gets a little annoying
to say, “Hey Google” every time
I want to get my Assistant’s attention. This grandma,
who you might have seen on YouTube, was definitely feeling that way. – (woman) Googoo!
– (laughter) Hey Googoo! Googoo!
Hello Googoo! – (slowly) H-e-y Googoo.
– (laughter) Okay Googoo. – He wanna know what is the weather…
– (man) Tomorrow. (woman) Tomorrow. (Assistant) In Flagler Beach tomorrow, there’ll be showers
with a high of 65 and a low of 56. (laughter) – (Scott laughing)
– (laughter) Well, the Assistant
eventually worked for her. But, it shouldn’t be so hard. Now you won’t have to say,
“Hey Google” every time. Check this out. Hey Google.
Did the Warriors win? (Assistant) Yes,
the Warriors won 118 to 92 last Sunday against the Pelicans. (Scott) Nice!
When’s their next game? (Assistant) The Warriors’ next game
is today at 7:30 pm where they will be playing the Pelicans. (Scott) Great.
It’s going to be fun to watch tonight. Hey, remind me to find
my Kevin Durant jersey when I get home. (Assistant) Sure.
I’ll remind you when you get home. Now, notice that I was able to have
a natural, back-and-forth conversation with my Assistant, without having to repeat “Hey Google”
for every followup request. Even more helpful– my Assistant could understand
when I was talking to it versus when I was talking to all of you. We call this Continued Conversation and it’s been a top feature request. You’ll be able to turn it on
in the coming weeks. (applause) So, let’s say it’s almost game time. Hey Google. Turn on the Warriors game
and start the popcorn maker. (Assistant) Sure.
Here’s the Golden State Warriors game on YouTube TV
and turning the popcorn maker on. (Scott) Oh, and can you dim the lights
in the family room and in the kitchen? (Assistant) Sure. Dimming the lights
in the family room and in the kitchen. (Scott) Now, you’ll notice
in both of these examples I asked for multiple things at once– something
that feels really natural for us, but it’s very difficult
for computers to understand. It’s something we call Multiple Actions and we’re rolling out this capability
in the Assistant now. You might think, “Come on, it’s easy!
Just look for the ‘and’.” (laughter) But it’s not always so straightforward. In this example,
even though it has the word “and,” it’s not two requests–
it’s actually just one. But here, even though it looks very similar, the Assistant has to break it apart to form the two requests. In linguistics it’s called
“coordination reduction.” Multiple actions
can get way more complicated so, just for fun– Hey Google. Who was the governor of California
when Kevin Durant was drafted, and what team drafted him? (Assistant) Arnold Schwarzenegger
was the governor in 2007. Kevin Durant was drafted
by the Seattle Super Sonics. (Scott) Alright.
Just in case you were wondering. (applause) Alright. Next. We’ve also been working on improving the conversation
with the Google Assistant for families. Last fall, we launched our Family experience for the Google Assistant. It provides family-friendly games,
activities, and stories. We’ve continued to grow our library, and families have listened to
over 130,000 hours of children’s stories in the last two months alone. Now, as we continue
to improve the experience for families, a concern that we’ve heard
from many parents– including people on the team
who have children– is are kids learning
to be bossy and demanding when they can just say, “Hey Google”
to ask for anything they need? It’s not a simple area, but one step that we’ve been working on
is something we call “Pretty Please.” Some of the parents on the team have been
testing it out with their families. Take a look. Hey Google.
Talk to [inaudible]. Daddy, you forgot to say please. Okay Google.
Please tell me a story. (Assistant) Thanks for saying please. Play “Freeze Dance,” please. (Assistant) What a nice way to ask me. Tell me a story, please. (Assistant) Thanks for asking so nicely. Once upon a time,
there was a wacky walrus… Please help me with my homework. Please… – Please…
– Please… (Assistant) You’re very polite. I know. ♪ (music) ♪ (laughter) (Scott) So, the Assistant understands and responds to positive conversation
with polite reinforcement. We’ve been consulting with families
and child development experts, and we plan to offer Pretty Please
as an option for families later this year. So, with new voices for your Assistant, Continued Conversation, Multiple Actions and Pretty Please, AI is helping us make big strides so everyone can have
a more natural conversation with their Assistant. And now I’d like to introduce Lilian, who’s going to share
some exciting things we’re doing, bringing Voice
and Visual Assistance together. ♪ (music) ♪ Well, thanks Scott,
and good morning everyone. Over the last couple of years
the Assistant has been focused on the verbal conversation
that you can have with Google. Today, we’re going to unveil
a new visual canvas for the Google Assistant across screens. This will bring the simplicity of Voice
together with a rich visual experience. I’m going to invite Meggy to come up because we’re going to be switching
to a lot of live demos. We gave you an early look
at our new Smart Displays at CES in January. We’re working with some of the best
consumer electronic brands, and today I’m excited to announce
that the first Smart Displays will go on sale in July. Today, I’ll show you some of the ways
that this new device can make your day easier, by bringing the simplicity of Voice with the glanceability of a touch screen. Let’s switch over to the live demos. Now, this is one
of the Lenovo Smart Displays. The ambient screen
integrates with Google Photos and greets me with pictures of my kids,
Bella and Hudson– those are really my kids. Best way to start my day every morning. Because the device is controlled by voice, I can watch videos or live TV
with just a simple command. This makes it so easy
to enjoy my favorite shows while multitasking around the house. Hey Google.
Let’s watch Jimmy Kimmel Live. (Assistant) Okay,
playing Jimmy Kimmel Live on YouTube TV. (applause coming via the device) (Jimmy) I had a funny thing happen.
Here’s something from my life– I was driving my daughter
to school this morning… (Lilian) That’s right. On YouTube TV you will be able
to watch all of these amazing shows, from local news, live sports,
and much more, and they will be available
on Smart Displays. Now, of course you can also enjoy
all the normal content from YouTube, including How-to videos, music,
and original shows, like the brand new series Cobra Kai which we started binge watching this week
because it’s so good. (laughs) Now, cooking is another instance
where the blend of voice and visuals is incredibly useful. Nick and I are always looking
for simple family-friendly recipes. Hey Google. Show me recipes for pizza bombs. (Assistant) Sure.
Here are some recipes. (Lilian) So we can choose the first one
from Tasty– that looks good. You see the recipe details come right up
and we can just tap to start cooking. (Assistant) Sure, here’s Tasty. So, seeing a video demonstration
along with spoken instructions is a total game changer for cooking, especially when you have your hands full. Thanks, Meggy. (applause) We showed you a couple of ways
that Smart Displays can make life at home easier, but there are so many more, from staying in touch with family
with Broadcast and Dual Video Calling, to keeping an eye on your home
with all of our other Smart Home partners, to seeing in advance what the morning
commute’s like with Google Maps. We’re thoughtfully integrating
the best of Google, and working with developer and partners
all around the world to bring Voice and Visuals together
in a completely new way for the home. Now, inspired by
the Smart Display experiences, we’ve also been working
to reimagine the Assistant experience on the screen
that’s with us all the time– our mobile phones. I’m going to give you a sneak peak
into how the Assistant on the phone is becoming more immersive,
interactive, and proactive. So, we’re going to switch
to another live demo. Hey Google, tell me about Camila Cabello. (Assistant) According to Wikipedia, Karla Camila Cabello Estrabao
is an American singer and songwriter. As you can see,
we’re taking full advantage of the screen to give you a rich and immersive response. Here’s another. Turn down the heat. (Assistant) Sure.
Cooling the living room down. For Smart Home requests
what you can see here is we’re bringing the controls
right into your fingertips. And here’s one of my favorites. Hey Google.
Order my usual from Starbucks. (Assistant) Hello.
Welcome back to Starbucks. That’s one tall, non-fat latte
with caramel drizzle. Anything else? No, thanks. (Assistant) And, are you
picking that up at the usual place? So, I’m going to tap Yes. (Assistant) Okay, your order’s in. See you soon. – (applause)
– Yeah! We’re excited to share
that we’ve been working with Starbucks, Dunkin’ Donuts, DoorDash, Domino’s
and many other partners on a new food pick up and delivery
experience for the Google Assistant. We have already
started rolling some of these out, with many more partners coming soon. Now, rich and interactive
responses to my requests are really helpful, but my ideal Assistant should also
be able to help in a proactive way. So, when I’m in the Assistant now,
and swipe up, I now get a visual snapshot of my day. I see helpful suggestions
based on the time, my location, and even my recent interactions
with the Assistant. I also have my reminders, packages, and even notes and lists,
organized and accessible right here. I love the convenience
of having all these details helpfully curated and so easy to get to. This new visual experience for the phone is thoughtfully designed
with AI at the core. It will launch on Android this summer,
and iOS later this year. (applause) Now, sometimes the Assistant
can actually be more helpful by having a lower visual profile. So, when you’re in the car,
you should stay focused on driving. So, let’s say I’m heading home from work. I have Google Maps showing me
the fastest route during rush hour traffic. Hey Google. Send Nick my ETA
and play some hip-hop. (Assistant) Okay.
Letting Nick know you’re 20 minutes away and check out
this hip-hop music station on YouTube. ♪ (hip-hop music) ♪ So, it’s so convenient
to share my ETA with my husband with just a simple voice command. I’m excited to share that the Assistant
will come to navigation in Google Maps this summer. (applause) So, across Smart Displays,
phones, and in Maps, this gives you a sense
of how we’re making the Google Assistant more visually assistive, sensing when to respond with voice, and when to show a more immersive
and interactive experience. And with that I’ll turn it
back to Sundar. Thank you. ♪ (music) ♪ Thanks, Lilian. It’s great to see
the progress with our Assistant. As I said earlier,
our vision for our Assistant is to help you get things done. It turns out, a big part
of getting things done is making a phone call. You may want to get an oil change schedule, maybe call a plumber
in the middle of the week, or even schedule a haircut appointment. We are working hard
to help users through those moments. We want to connect users
to businesses in a good way. Businesses actually rely a lot on this, but even in the US, 60% of small businesses don’t have
an online booking system set up. We think AI can help with this problem. So, let’s go back to this example. Let’s say you want to ask Google
to make you a haircut appointment on Tuesday between 10 and noon. What happens is the Google Assistant makes the call seamlessly
in the background for you. So, what you’re going to hear is the Google Assistant
actually calling a real salon to schedule an appointment for you. – (cheering)
– Let’s listen. (ringing tone) (woman) Hello, how can I help you? (Assitant) Hi, I’m calling
to book a women’s haircut for our client. I’m looking for something on May 3rd. (woman) Sure, give me one second. – (Assistant) Mm-hmm.
– (laughter) (woman) Sure.
What time are you looking for, around? (Assistant) At 12 pm. We do not have a 12 pm available. The closest we have to that is a 1:15. (Assistant) Do you have anything
between 10 am and 12 pm? (woman) Depending on
what service she would like. What service is she looking for? (Assistant)
Just a women’s haircut, for now. (woman) Okay, we have a 10 o’ clock. – (Assistant) 10 am is fine.
– (woman) Okay, what’s her first name? (Assistant)
The first name is Lisa. (woman) Okay, perfect, so I will see Lisa
at 10 o’ clock on May 3rd. – (Assistant) Okay great, thanks.
– (woman) Great, have a great day, bye. (applause) That was a real call you just heard. The amazing thing is the Assistant
can actually understand the nuances of conversation. We’ve been working on this technology
for many years. It’s called Google Duplex. It brings together
all our investments over the years on natural language understanding, deep learning, textured speech. By the way, when we are done
the Assistant can give you a confirmation notification saying
your appointment has been taken care of. Let me give you another example. Let’s say you want to call a restaurant,
but maybe it’s a small restaurant which is not easily available
to book online. The call actually
goes a bit differently than expected. So, take a listen. (ringing tone) (woman) Hi, may I help you? (Assistant) Hi, I’d like to reserve
a table for Wednesday, the 7th. (woman) For seven people? (Assistant) Um, it’s for four people. (woman) Four people?
When? Today? Tonight? (Assistant) Um, next Wednesday, at 6 pm. (woman) Actually, we reserve
for upwards of five people. For four people, you can come. (Assistant) How long is the wait
usually to be seated? (woman) For when?
Tomorrow? Or weekend, or..? (Assistant) For next Wednesday,
uh, the 7th. (woman) Oh no, it’s not too busy.
You can come for four people, okay? – (Assistant) Oh, I gotcha. Thanks.
– (woman) Yep. Bye-bye. (laughter) (cheering) Again, that was a real call. We have many of these examples,
where the calls quite don’t go as expected but the Assistant
understands the context, the nuance, it knew to ask
for wait times in this case, and handled the interaction gracefully. We’re still developing this technology, and we actually want to work hard
to get this right– get the user experience
and the expectation right for both businesses and users. But, done correctly,
it will save time for people, and generate
a lot of value for businesses. We really want it to work in cases, say,
if you’re a busy parent in the morning and your kid is sick and you want to call
for a doctor’s appointment. So, we’re going to work hard
to get this right. There is a more straightforward case
where we can roll this out sooner, where, for example, every single day
we get a lot of queries into Google where people are wondering
on the opening and closing hours of businesses. But it gets tricky during holidays and businesses get a lot of calls. So, we as Google,
can make just that one phone call and then update the information
for millions of users and it will save a small business
countless number of calls. So, we’re going
to get moments like this right, and make the experience better for users. This is going to be rolling out
as an experiment in the coming weeks. And so, stay tuned. (applause) A common theme across all this is we are working hard
to give users back time. We’ve always been obsessed
about that at Google. Search is obsessed
about getting users the answers quickly and giving them what they want. Which brings me to another area–
Digital Wellbeing. Based on our research, we know that people
feel tethered to their devices. I’m sure it resonates with all of you. There is increasing social pressure to respond to anything you get right away. People are anxious to stay up to date with all the information out there. They have FOMO– Fear of Missing Out. We think there’s a chance
for us to do better. We’ve been talking to people, and some people introduced to us
the concept of JOMO– the actual Joy of Missing Out. (chuckles) (laughter) So, we think we can really help users
with digital wellbeing. This is going to be a deep, ongoing effort across all our products and platforms, and we need all your help. We think we can help users
with their digital wellbeing in four ways. We want to help you
understand your habits, focus on what matters, switch off when you need to, and, above all,
find balance with your family. So, let me give a couple of examples. You’re going to hear about this
from Android a bit later, in their upcoming release. But one of my favorite features
is Dashboard. In Android, we’re actually
going to give you full visibility into how you’re spending your time– the apps where you’re spending your time, the number of times you unlock your phone
on a given day, the number of notifications you got, and we’re going to really help you
deal with this better. Apps can also help. YouTube is going to take the lead, and if you choose to do so, it’ll actually remind you to take a break. So, for example, if you’ve been
watching YouTube for a while, maybe it’ll show up and say,
“Hey, it’s time to take a break.” YouTube is also going to work to combine–
if users want to– combine all their notifications in the form of a daily digest, so that if you have four notifications,
it comes to you once during the day. YouTube is going to roll out
all these features this week. (applause) We’ve been doing a lot of work in this area. Family Link is a great example, where we provide parents tools to help manage kids’ screen time. I think this is an important part of it. We want to do more here, we want to equip kids
to make smart decisions. So, we have a new approach–
a Google design approach. It’s called Be Internet Awesome, to help kids become safe explorers
of the digital world. We want kids to be secure, kind,
mindful, when online. And we are pledging to train
an additional 5 million kids this coming year. All these tools you’re seeing are launching with our Digital Wellbeing site later today. Another area where we feel
tremendous responsibility is news. News is core to our mission. Also, at times like this, it’s more important than ever to support quality journalism. It’s foundational to how democracies work. I’ve always been fond of news. Growing up in India, I have distinct memory of–
I used to wait for the physical newspaper. My grandfather
used to stay right next to us. There was a clear hierarchy. He got his hands on the newspaper first, then my dad, and then my brother and I would go at it. I was mainly interested
in the sports section at that time, but over time
I developed a fondness for news, and it stayed with me even till today. It is a challenging time
for the news industry. Recently, we launched
Google News Initiative, and we committed 300 million dollars
over the next three years. We want to work with organizations
and journalists to help develop
innovative products and programs that help the industry. We’ve also had a product here
for a long time– Google News. It was actually built right after 9/11. It was a 20-person project
by one of our engineers who wanted to see news
from a variety of sources to better understand what happened. Since then, if anything, the volume
and diversity of content has only grown. I think there is more great journalism
being produced today than ever before. It’s also true that people
turn to Google in times of need and we have a responsibility
to provide that information. This is why we have re-imagined
our News Project. We are using AI to bring forward
the best of what journalism has to offer. We want to give users
quality sources that they trust, but we want to build a product
that works for publishers. Above all, we want to make sure
we’re giving them deeper insight and a fuller perspective about any topic they’re interested in. I’m really excited to announce
the new Google News, and here’s Trystan to tell you more. ♪ (music) ♪
(applause) Thank you, Sundar. With the new Google News,
we set out to help you do three things: First, keep up with the news you care about. Second, understand the full story. And, finally, enjoy and support
the sources you love. After all, without news publishers and the quality journalism they produce, we’d have nothing to show you here today. Let’s start with how
we’re making it easier for you to keep up with the news you care about. As soon as I open Google News, right at the top, I get a briefing with the top five stories
I need to know right now. As I move past my briefing, there are more stories selected just for me. Our AI constantly reads
the firehose of the web for you– the millions of articles, videos,
podcasts, and comments being published every minute– and assembles the key things
you need to know. Google News also pulls in local voices
and news about events in my area. It’s this kind of information that
makes me feel connected to my community. This article from The Chronicle
makes me wonder how long it would take
to ride across this new Bay Bridge. What’s cool is I didn’t have to tell the app that I follow politics, love to bike,
or want information about the Bay area– it works right out of the box. And, because we’ve applied techniques like
reinforcement learning throughout the app, the more I use it, the better it gets. At any point, I can jump in and say
whether I want to see less or more of a given publisher or topic. And whenever I want to see
what the rest of the world is reading, I can switch over to Headlines to see the top stories
that are generating the most coverage right now, around the world. So, let’s keep going. You can see
there are lots of big, gorgeous images that make this app super engaging, and a truly great video experience. Let’s take a look. (music and cheering via the device) This brings you
all the latest videos from YouTube and around the web. All of our design choices
focus on keeping the app light, easy, fast, and fun. Our guiding principle is to
let the stories speak for themselves. So, it’s pretty cool, right? (applause) What we’re seeing here throughout the app
is the new Google Material Theme. The entire app is built
using Material design– our adaptable, unified design system that’s been uniquely tailored by Google. Later today, you’ll hear more about this and how you can use Material themes
in your products. We’re also excited to introduce
a new visual format we call Newscasts. You’re not going to see these
in any other news app. Newscasts are kind of like
a preview of the story, and they make it easier for you
to get a feel for what’s going on. Check out this one on the Star Wars movie. Here we’re using the latest developments
in natural language understanding to bring together everything, from the Solo movie trailer, to news articles, to quotes–
from the cast and more– in a fresh presentation
that looks absolutely great on your phone. Newscasts give me an easy way
to get the basics and decide
where I want to dive in more deeply. And sometimes I even discover things
I never would have found out otherwise. For the stories I care about most, or the ones that are really complex, I want to be able to jump in
and see many different perspectives. So, let’s talk about our second goal
for Google News– understanding the full story. Today, it takes a lot of work
to broaden your point of view and understand a news story in-depth. With Google news, we set out
to make that effortless. Full Coverage is an invitation to learn more. It gives a complete picture of a story in terms of how it’s being reported
from a variety of sources, and in a variety of formats. We assemble Full Coverage using a technique
we call temporal co-locality. This technique enables us
to map relationships between entities and understand the people,
places, and things in a story right as it evolves. We applied this to the deluge
of information published to the web at any given moment and then organize it around story lines– all in real time. This is by far
the most powerful feature of the app, and provides a whole new way
to dig into the news. Take a look at how Full Coverage works for the recent power outage
in Puerto Rico. There are so many questions
I had about this story, like, “How did we get here?” “Could it have been prevented?” and, “Are things actually getting better?” We built Full Coverage
to help make sense of it all, all in one place. We start out with a set of top headlines
that tell me what happened, and then start to organize
around the key story aspects using our real time event understanding. For news events that have played out,
like this one, over weeks and months, you can understand
the origin of developments, by looking at our timeline
of the key moments. And while the recovery has begun, we can clearly see
there’s still a long way to go. There are also certain questions
we are all asking about a story, and we pull those out
so you don’t have to hunt for the answers. We know context and perspective
come from many places, so we show you Tweets
from relevant voices, and opinions, analysis, and fact checks, to help you understand the story
that one level deeper. In each case, our AI is highlighting why
this is an important piece of information and what unique value it brings. Now, when I use Full Coverage, I find that I can build
a huge amount of knowledge on the topics I care about. It’s a true 360 degree view that goes well beyond what I get
from just scanning a few headlines. On top of this, our research shows that having
a productive conversation or debate requires everyone
to have access to the same information. Which is why
everyone sees the same content in Full Coverage for a topic. It’s an unfiltered view of events
from a range of trusted news sources. (applause) Thank you. So, I’ve got to say–
I love these new features. And these are just a few of the things
we think make the new Google News so exciting. But, as we mentioned before, none of this would exist
without the great journalism news rooms produce every day. Which brings us to our final goal– helping you enjoy and support
the news sources you love. We’ve put publishers front and center
throughout the app, and here in the Newsstand section, it’s easy to find and follow
the sources I already love, and browse and discover new ones. including over 1,000 magazine titles, like Wired,
National Geographic, and People, which all look great on my phone. I can follow publications like USA Today
by directly tapping the star icon. And, if there’s a publication
I want to subscribe to– say, The Washington Post, we make it dead simple. No more forms, credit card numbers,
or new passwords, because you’re signed in
with your Google account, you’re set. When you subscribe to a publisher, we think you should have easy access
to your content everywhere. And this is why we developed
Subscribe with Google. Subscribe with Google
enables you to use your Google account to access your paid content everywhere, across all platforms and devices
on Google Search, Google News, and publishers’ own sites. We built this in collaboration
with over 60 publishers around the world and it will be rolling out
in the coming weeks. (applause) Thank you. And this is one
of the many steps we’re taking to make it easier to access
dependable, high quality information, when and where it matters most. So, that’s the new Google News. It helps you keep up
with the news you care about, with your Briefing and Newscasts, understand the full story,
using Full Coverage, and enjoy and support
the news sources you love, by reading, following, and subscribing. And now, for the best news of all, we’re rolling out
on Android, iOS and the web, in 127 countries, starting today. (cheering) I think so, too.
Pretty cool. It will be available
to everyone next week. At Google, we know that
getting accurate and timely information into people’s hands, and building and supporting
high quality journalism is more important
than it ever has been right now. And we are totally committed
to doing our part. We can’t wait
to continue on this journey with you. And now, I’m excited to introduce Dave to tell you more
about what’s going on in Android. (applause) (man) Android started with the simple goal of bringing open standards
to the mobile industry. Today, it is the most popular
mobile operating system in the world. ♪ (uplifting music) ♪ (man) If you believe in openness, if you believe in choice, if you believe
in innovation from everyone, then welcome to Android. (applause) ♪ (music) ♪ Hi everyone.
It’s great to be here at Google I/O 2018. (cheering) Ten years ago,
when we launched the first Android phone, the T-Mobile G1, it was with a simple but bold idea– to build a mobile platform
that was free and open to everyone. And, today, that idea is thriving. Our partners have launched
tens of thousands of smartphones, used by billions of people
all around the world. And through this journey we’ve seen
Android become more than just a smartphone operating system. powering new categories of computing,
including wearables, TV, auto, ARVR, IoT. And the growth of Android
over the last ten years has helped fuel the shift in computing from desktop to mobile. And, as Sundar mentioned, the world
is now on the precipice of another shift. AI is going to profoundly change industries like healthcare and transport. It is already starting to change ours. And this brings me to the new version
of Android we’re working on– Android P. Android P is an important first step towards this vision of AI
at the core of the operating system. In fact, AI underpins the first
of three themes in this release, which are: Intelligence, Simplicity, and Digital wellbeing. So, starting with intelligence. We believe smartphones should be smarter. They should learn from you
and they should adapt to you. Technologies
such as on-device machine learning can learn your usage patterns, and automatically anticipate
your next actions, saving you time. And, because it runs on device, the data is kept private to your phone. So, let’s take a look at some examples of how we’re
applying these technologies to Android to build a smarter operating system. In pretty much every survey
of smartphone users, you’ll see battery life
as the top concern. And, I don’t know about you,
but this is my version of Maslow’s hierarchy of needs. (laughter) And we’ve all been there. Your battery’s been okay, but then
you have one of those outlier days, where it’s draining faster than normal,
leaving you to run to the charger. With Android P
we partnered with Deep Mind to work on a new feature
we call Adaptive Battery. It’s designed to give you
a more consistent battery experience. Adaptive battery
uses on-device machine learning to figure out which apps
you’ll use in the next few hours, and which you won’t use until later,
if at all, today. And then, with this understanding, the operating system
adapts to your usage patterns. so that it spends battery
only the apps and services that you care about. And the results are really promising. We’re seeing a 30% reduction
in CPU wake-ups for apps in general. And this, combined
with other performance improvements, including running background processes
on the small CPU cores, is resulting in an increase in battery
for many users. It’s pretty cool. Another example
of how the OS is adapting to the user is auto-brightness. Now, most modern smartphones
will automatically adjust the brightness, given the current lighting conditions. But it’s a one-size-fits-all. They don’t take into account
your personal preferences and environment. So, often what happens, is you then need
to manually adjust the brightness slider, resulting in the screen
later becoming too bright or too dim. With Android P, we were introducing
a new on-device machine learning feature we call Adaptive Brightness. Adaptive Brightness learns
how you like to set the brightness slider, given the ambient lighting, and then does it for you in a power-efficient way. So, you’ll literally see
the brightness slider move as the phone adapts to your preferences. And it’s extremely effective. In fact, we’re seeing
almost half of our test users now make fewer manual brightness adjustments, compared to any previous version of Android. We’re also making the UI more intelligent. Last year we introduced the concept
of predicted apps, a feature that places the next apps
the OS anticipates you need on the path you’d normally follow to launch that app. And it’s very effective, with an almost 60% prediction rate. With Android P, we’re going beyond
simply predicting the next app to launch, to predicting the next action
you want to take. We call this feature App Actions. Let’s take a look at how it works. At the top of the launcher
you can see two actions– one, to call my sister, Fiona, and another to start a workout on Strava,
for my evening run. So, what’s happening here
is that the actions are being predicted based on my usage patterns. The phone is adapting to me
and trying to help me get to my next task more quickly. As another example,
if I connect my headphones, Android will surface an action
to resume the album I was listening to. To support App Actions, developers just need to add
an actions.xml file to their app. And then Actions surfaces
not just in the Launcher, but in Smart Text selection,
the Play Store, Google Search, and the Assistant. Take Google Search. We’re experimenting with different ways
to surface actions for apps you’ve installed and use a lot. For example, I’m a big Fandango user. So, when I search for the new
Avengers movie, Infinity War, I get, in addition to regular suggestions, I get an action to the Fandango app to buy tickets. Pretty cool. Actions are a simple but powerful idea for providing deep links into the app given your context. But even more powerful
is bringing part of the app UI to the user, right there and then. We call this feature Slices. Slices are a new API for developers to define
interactive snippets of their app UI. They can be surfaced
in different places in the OS. In Android P, we’re laying the groundwork
by showing slices first in Search. So, let’s take a look. Let’s say I’m out and about
and I need to get a ride to work. If I type “lyft”
into the Google Search app, I now see a slice from the Lyft app
installed on my phone. Lyft is using the Slice API’s rich array
of UI templates to render a slice of their app
in the context of Search. And then Lyft is able to give me
the price for my trip to work, and the slice is interactive,
so I can order the ride directly from it. Pretty nice. The Slice templates are versatile
so developers can offer everything from playing a video to,
say, checking into a hotel. As another example– if I search for Hawaii, I’ll see a slice from Google Photos
with my vacation pictures. And we’re working with some amazing partners on App Actions and Slices. And we’ll be opening
an early-access program to developers more broadly next month. So, we’re excited to see
how Actions and, in particular, Slices, will enable a dynamic two-way experience where the app’s UI
can intelligently show up in context. So, that’s some of the ways
that we’re making Android more intelligent by teaching the operating system to adapt to the user. Machine learning’s a powerful tool, but it can also be intimidating and costly for developers to learn and apply. And we want to make these tools accessible and easy to use to those who have little or no expertise in machine learning. So, today I’m really excited
to announce ML Kit, a new set of APIs
available through Firebase. With ML Kit, you get on-device APIs, to text recognition, and face detection, image labeling, and a lot more. And ML Kit also supports the ability to tap into Google’s
cloud-based ML technologies. Architecturally, you can think of ML Kit as providing ready-to-use models, built on TensorFlow Lite and optimized for mobile. And, best of all,
ML Kit is cross platform, so it runs on both Android and iOS. (cheering) We’re working with
an early set of partners on ML Kit with some really great results. For example, the popular
calorie counting app, Lose It! is using our text recognition model to scan nutritional information, and ML Kits custom-model APIs to automatically classify 200 different foods through the camera. You’ll hear more about ML Kit
at the developer keynote later today. So, we’re excited about
making your smartphone more intelligent, but it’s also important to us
that the technology fades to the back. One of our key goals over the last few years has been to evolve Android’s UI
to be simpler and more approachable, both for the current set of users, and the next billion Android users. With Android P, we put a special emphasis on simplicity by addressing many pain points
where we thought– and you told us– the experience
was more complicated than it ought to be. And you’ll find these improvements
on any device that adopts Google’s version of the Android UI, such as Google Pixel and Android One devices. So, let me walk you through
a few live demos on my phone. What could possibly go wrong in front of 7,000 people in an amphitheater? Okay. (laughs) As part of Android P,
we’re introducing a new system navigation that we’ve been working on
for more than a year now. And the new design makes
Android’s multitasking more approachable and easier to understand. And the first striking thing you’ll notice is the single, clean Home button. And the design recognizes a trend
towards smaller screen bezels and places an emphasis on gestures over multiple buttons
at the edge of the screen. So, when I swipe up, I’m immediately brought to the Overview, where I can resume apps I’ve recently used. I also get five predicted apps
at the bottom of the screen to save me time. Now, if I continue to swipe up,
or I swipe up a second time, I get to All Apps. So, architecturally, what we’ve done is combine the All Apps
and Overview spaces into one. The swipe up gesture works from anywhere, no matter what app I’m in so that I can quickly get back
to All Apps and Overview without losing the context I’m in. And, if you prefer, you can also use the Quick Scrub gesture by sliding the Home button sideways to scroll through
your recent set of apps like so. (applause) Now, one of the nice things
about the larger horizontal Overview is that the app content is now glanceable, so you can easily refer back
to information in a previous app. Even more is we’ve extended
Smart Text Selection to work in Overview. So, for example, if I tap anywhere
on the phrase, The Killers, all of the phrase will be selected for me, and then I get an action
to listen to it on Spotify, like so. And we’ve extended Smart Text Selection’s
neural network to recognize more entities, like sports teams and music artists,
and flight codes and more. I’ve been using this View
navigation system for the last month, and I absolutely love it. It’s a much faster, more powerful way to multitask on the go. So, changing how Navigation works–
it’s a pretty big deal. But sometimes small changes
can make a big difference, too. So, take volume control. We’ve all been there–
you try to turn down the volume before a video starts, but instead, you turn down the ringer volume and then the video
blasts everyone around you. So, how are we fixing it? Well, you can see
the new simplified volume controls here. They’re vertical,
and located beside the hardware buttons– so they’re intuitive. But the key difference is that the slider
now adjusts the media volume by default, because that’s the thing
you want to change most often. And, for the ringer volume,
all you really care about is On, Silent, and Off, like so. Okay. We’ve also greatly simplified rotation. And, if you’re like me, and hate your device
rotating at the wrong time you’ll love this feature. So, right now, I’m in the Lock Rotation mode. And let me launch an app, and you’ll notice
that when I rotate the device, a new Rotation button appears on the Nav bar. And then I can just tap on it
and rotate under my own control. It’s pretty cool. (applause) Alright, so that’s a quick tour of some of the ways that we’ve simplified
user experience in Android P. And there’s lots more. Everything from a redesigned work profile, to better screenshots, to improved
notifications management, and more. Speaking of notifications management, we want to give you more control
over demands on your attention. And this highlights a concept
that Sundar alluded to earlier– making it easier
to move between your digital life and your real life. To learn more about this important area, and our third theme,
let me hand over to Sameer. Thanks. (applause) ♪ (music) ♪ Hi everyone! On a recent family vacation, my partner asked if she could see my phone right after we got to our hotel room. She took it from me, walked over to the hotel safe, locked it inside, and turned and looked me
right in the eye and said, “You get this back
in seven days when we leave.” (laughter) Whoa! I was shocked. I was kind of angry. But after a few hours,
something pretty cool happened. Without all the distractions
from my phone, I was actually able to disconnect, be fully present, and I ended up
having a wonderful family vacation. But it’s not just me. Our team has heard
so many stories from people who are trying to find
the right balance with technology. As you heard from Sundar, helping people with their digital wellbeing is more important to us than ever. People tell us a lot of the time
they spend on their phone is really useful. But some of it
they wish they’d spent on other things. In fact, we found over 70% of people want more help striking this balance. So, we’ve been working hard to add key capabilities right into Android to help people
find the balance with technology that they’re looking for. One of the first things we focused on was helping you understand your habits. Android P will show you a Dashboard of how you’re spending time on your device. As you saw earlier, you can see how much time you spent in apps, how many times
you’ve unlocked your device today, and how many notifications you’ve received. And you can drill down
on any of these things. For example,
here’s my Gmail data from Saturday. And when I saw this it did make me wonder
whether I should’ve been on my email all weekend. But that’s kind of the point
of the Dashboard. Now, when you’re engaging
is one part of understanding. But what you’re engaging with in apps is equally important. It’s like watching TV– catching up on your favorite shows
at the end of a long day can feel pretty good. But watching an infomercial
might leave you wondering why you didn’t do something else instead. Many developers call this concept
“meaningful engagement.” And we’ve been working closely
with many of our developer partners who share the goal of helping people use technology
in healthy ways. So, in Android P, developers can link
to more detailed breakdowns of how you’re spending time in their app from this new Dashboard. For example,
YouTube will be adding a deep link where you can see total watch time across mobile and desktop and access many of the helpful tools that Sundar shared earlier. Now, understanding is a good start. But Android P also gives you controls to help you manage
how and when you spend time on your phone. Maybe you have an app that you love, but you’re spending more time in it
than you realize. Android P lets you set
time limits on your apps and will nudge you
when you’re close to your limit that it’s time to do something else. And, for the rest of the day, that app icon is grayed out, to remind you of your goal. People have also told us
they struggle to be fully present for the dinner that they’re at
or the meeting that they’re attending, because the notifications
they get on their device can be distracting and too tempting to resist. Come on– we’ve all been there. So we’re making improvements to Do Not Disturb mode, to silence not just
the phone calls and texts, but also the visual interruptions
that pop up on your screen. To make Do Not Disturb even easier to use, we’ve created a new gesture that we’ve affectionately
code-named Shush. (laughter) If you turn your phone over on the table,
it automatically enters Do Not Disturb so you can focus on being present– no pings, vibrations, or other distractions. (applause) Of course, in an emergency, we all want to make sure we’re still
reachable by the key people in our lives, like your partner or your child’s school. Android P will help you
set up a list of contacts that can always
get through to you with a phone call, even if Do Not Disturb is turned on. Finally, we heard from people
that they often check their phone right before going to bed, and, before you know it, an hour or two has slipped by. And, honestly, this happens to me
at least once a week. Getting a good night’s sleep is critical, and technology should help you with this, not prevent it from happening. So, we created Wind Down mode. You can tell the Google Assistant
what time you aim to go to bed, and when that time arrives
it will switch on Do Not Disturb, and fade the screen to gray scale, which is far less stimulating for the brain, and can help you set the phone down. It’s such a simple idea, but I found it’s amazing
how quickly I put my phone away when all my apps
go back to the days before color TV. (laughter) (applause) Don’t worry, all the colors
return in the morning when you wake up. Okay, that was a quick tour
of some of the digital wellbeing features we’re bringing to Android P this fall, starting with Google Pixel. Digital wellbeing is going to be
a long term theme for us, so look for much more to come in the future. Beyond the three themes
of intelligence, simplicity, and digital wellbeing
that Dave and I talked about, there are literally hundreds
of other improvements coming in Android P. I’m especially excited about the security
advancements we’ve added to the platform, and you can learn more about them
at the Android Security session on Thursday. But your big question is: That’s all great. How do I try some of this stuff? Well, today we’re announcing
Android P Beta. (applause) And with efforts in Android Oreo
to make OS upgrades easier, Android P Beta
is available on Google Pixel and seven more
manufacturer flagship devices today. (applause) You can head over to this link to find out how
to receive the Beta on your device, and please do let us know what you think. Okay, that’s a wrap
on what’s new at Android, and now I’d like to introduce Jen
to talk about Maps. Thank you. (applause) ♪ (music) ♪ (woman) It has changed Nigeria so much
and you can actually be part of it. (man) Being able to be armed
with the knowledge of where you’re going, you’re going to be able to get there
like anybody else can. (man) Two consecutive earthquakes
hit Mexico City and Google Maps helped the response
to emergency crises like this. (woman) The hurricane hit
turned Houston into islands and the roads were changing constantly. We kept saying, “Thank God for Google!”
What would we have done? (man) It’s really cool
that this is helping people to keep doing what they love doing
and keep doing what they need to do. ♪ (music) ♪ (applause) Building technology to help people
in the real world, every day, has been core to who we are and what we’ve focused on at Google from the very start. Recent advancements in AI
and computer vision have allowed us to dramatically
improve long-standing products like Google Maps, and have also made possible
brand new products, like Google Lens. Let’s start with Google Maps. Maps was built to assist everyone, wherever they are in the world. We’ve mapped
over 220 countries and territories, and put hundreds of millions
of businesses and places on the map. And, in doing so,
we’ve given more than a billion people the ability to travel the world with the confidence
that they won’t get lost along the way. But we’re far from done. We’ve been making Maps
smarter and more detailed as advancements in AI have accelerated. We’re now able to automatically add
new addresses, businesses, and buildings that we extract from Street View
and satellite imagery directly to the Map. This is critical in rural areas, in places without formal addresses, and in fast-changing cities,
like Lagos here, where we’ve literally changed
the face of the map in the last few years. (cheering) Hello, Nigeria! (laughs) (laughter) We can also tell you if the business
you’re looking for is open, how busy it is, what the wait time is, and even how long
people usually spend there. We can tell you before you leave whether parking
is going to be easy or difficult, and we can help you find it. And we can now give you different routes
based on your mode of transportation, whether you’re riding a motorbike
or driving a car. And, by understanding how different types
of vehicles move at different speeds, we can make more accurate
traffic predictions for everyone. But we’ve only scratched the surface
of what Maps can do. We originally designed Maps
to help you understand where you are, and to help you get from here to there. But, over the past few years, we’ve seen our users
demand more and more of Maps. They’re bringing us harder
and more complex questions about the world around them,
and they’re trying to get more done. Today, our users aren’t just asking
for the fastest route to a place. They also want to know
what’s happening around them, what the new places to try are, and what locals love
in their neighborhood. The world is filled
with amazing experiences, like cheering for your favorite team
at a sports bar, or a night out with friends or family
at a cosy neighborhood bistro. We want to make it easy for you
to explore and experience more of what the world has to offer. We’ve been working hard
on an updated version of Google Maps that keeps you in the know
on what’s new and trending in the areas you care about. It helps you find the best place for you, based on your context and interests. Let me give you a few examples
of what this is going to look like, with some help from Sophia. First, we’re adding a new tab
to Maps called For You. It’s designed to tell you
what you need to know about the neighborhoods you care about– new places that are opening, what’s trending now, and personal recommendations. Here, I’m being told about a cafe
that just opened in my area. If we scroll down, I see a list of the restaurants
that are trending this week. This is super useful, because,
with zero work, Maps is giving me ideas
to kick me out of my rut and inspire me to try something new. But how do I know
if a place is really right for me? Have you ever had the experience
of looking at lots of places, all with four-star ratings, and you’re pretty sure there’s some
you’re going to like a lot and others that maybe aren’t quite so great, but you’re not sure how to tell which ones? We’ve created a score called Your Match to help you find more places
that you’ll love. Your Match uses machine learning to combine what Google knows
about hundreds of millions of places with the information that I’ve added– restaurants I’ve rated, cuisines I’ve liked, and places that I’ve been to. If you click into the Match number, you’ll see reasons explaining
why it’s recommended just for you. It’s your personal score for places. And our early testers
are telling us that they love it. Now, you can confidently pick the places
that are best for you, whether you’re planning ahead or on the go and need to make
a quick decision, right now. Thanks so much, Sophia. (applause) The For You tab, and the Your Match score, are great examples
of how we can help you stay in the know and choose places with confidence. Now, another pain point
we often hear from our users is that planning with others
can be a real challenge. So, we wanted to make it easier
to pick a place together. Here’s how. Long press on any place to add it to a short list. Now, I’m always up for ramen, but I know my friends
have lots of opinions of their own, so I can add some more options
to give them some choices. When you’ve collected enough places
that you like share the list with your friends
to get their input, too. You can easily share,
with just a couple of taps, on any platform that you prefer. Then, my friends can add more places
that they want to, or just vote with one simple click
so we can quickly choose a group favorite. So now, instead of copying and pasting
a bunch of links and sending texts back and forth, decisions can be quick, easy, and fun. This is just a glimpse
of some of what’s coming to Maps on both Android and iOS later this summer. And we see this is just the beginning
of what Maps can do to help you make better decisions on the go and to experience the world in new ways, from your local neighborhood,
to the far-flung corners of the world. This discovery experience
wouldn’t be possible without small businesses. Because, when we help people
discover new places, we’re also helping local businesses
be discovered by new customers. These are businesses
like the bakery in your neighborhood, or the barbershop around the corner. These businesses
are the fabric of our communities and we’re deeply committed
to helping them succeed with Google. Every month, we connect users
to businesses nearby more than 9 billion times, including over a billion phone calls and 3 billion direction requests
to their stores. In the last few months,
we’ve been adding even more tools for local businesses to communicate
and engage with their customers in meaningful ways. You can now see daily posts
on events or offers from many of your favorite businesses. And soon you will be able
to get updates from them in the new For You stream, too. And, when you’re ready, you can easily book an appointment
or place an order with just one click. We’re always inspired to see
how technology brings opportunities to everyone. The reason we’ve invested
over the last 13 years in mapping every road,
every building, and every business, is because it matters. When we map the world,
communities come alive and opportunities arise in places
we never would have thought possible. And, as computing evolves, we’re going to keep challenging ourselves
to think of new ways that we can help you get things done
in the real world. I’d like to invite Aparna to the stage
to share how we’re doing this, both in Google Maps, and beyond. ♪ (music) ♪ The cameras in our smartphones– they connect us to the world around us
in a very immediate way. They help us save a moment,
capture memories, and communicate. But with advances
in AI and computer vision that you heard Sundar talk about, we said, “What if the cameras can do more? What if the cameras
can help us answer questions?” Questions like, “Where am I going?”
or, “What’s that in front of me?” Let me paint a familiar picture. You exit the subway. You’re already running late
for an appointment– or a tech company conference–
that happens. And then your phone says,
“Head south on Market Street.” So, what do you do? One problem– you have no idea
which way is south. So, you look down at the phone, you’re looking
at that blue dot on the map, and you’re starting to walk to see
if it’s moving in the same direction. If it’s not, you’re turning around. – (laughter)
– We’ve all been there. So, we asked ourselves, “Well,
what if the camera can help us here?” Our teams have been working really hard to combine the power of the camera,
the computer vision, with Street View and Maps to re-imagine Walking Navigation. So, here’s how it could look in Google Maps. Let’s take a look. – You open the camera…
– (cheering) You instantly know where you are. No fussing with the phone. All the information on the map,
the street names, the directions– right there in front of you. Notice that you also see the map
so that way you stay oriented. You can start to see nearby places–
so you see what’s around you. (applause) And, just for fun, our team’s been playing with the idea
of adding a helpful guide, like that there… (applause) …so that it can show you the way. Oh, there she goes! Pretty cool. Now, enabling these kinds
of experiences, though, GPS alone doesn’t cut it. So, that’s why we’ve been working on
what we call VPS– Visual Positioning System– that can estimate precise positioning
and orientation. One way to think about
the key insight here is, just like you and I,
when we’re in an unfamiliar place, you’re looking for visual landmarks. You’re looking for the storefront,
the building facade, et cetera. And it’s the same idea. VPS uses the visual features
in the environment to do the same, so that way we help you
figure out exactly where you are and get you exactly where you need to go.
Pretty cool. So, that’s an example
of how we’re using the camera to help you in Maps. But we think the camera
can also help you do more with what you see. That’s why we started working on Google Lens. Now, people are already using it
for all sorts of answers, and especially when the questions
are difficult to describe in words. Answers like, oh, that cute dog in the park– that’s a Labradoodle. Or, this building in Chicago
is the Wrigley Building, and it’s 425 feet tall– or, as my 9-year old son says these days, “That’s more than 60 Kevin Durants!” (laughter) Now, today Lens has the capability,
in Google products– like Photos and the Assistant– but we’re very excited that,
starting next week, Lens will be integrated
right inside the camera app on the Pixel, the new LG G7, and a lot more devices. This way, it makes it super easy
for you to use Lens on things right in front of you
already in the camera. Very excited to see this. Now, likewise, Vision is a fundamental shift
in computing for us. And it’s a multi-year journey, but we’re already making a lot of progress, so today I thought I’d show you
three new features in Google Lens that can give you more answers
to more types of questions, more quickly. Shall we take a look? Alright! Okay, first, Lens can now recognize
and understand words. Words are everywhere. If you think about it–
traffic signs, posters, restaurant menus, business cards. But now, with Smart Text Selection, you can now connect the words you see with the answers and actions you need. So, you can do things like copy and paste from the real world directly into your phone. – Just like that.
– (applause) Or, let’s say you’re looking at– or you can turn a page of words
into a page of answers. So, for example,
you’re looking at a restaurant menu, you can quickly tap around,
figure out every dish– what it looks like,
what are all the ingredients, et cetera. By the way, as a vegetarian,
good to know ratatouille is just zucchini and tomatoes. (chuckles) – (laughter)
– Really cool. Now, in these examples, Lens is not just understanding the shape
of characters and the letters, visually, it’s actually trying to get at the meaning
and the context behind these words. And that’s where
all the language understanding that you heard Scott talk about
really comes in handy. Okay, the next feature I want to talk about is called Style Match. And the idea is this. Sometimes, your question is not,
“Oh, what’s that exact thing?” Instead, your question is,
“What are things like it?” You’re at your friend’s place,
you check out this trendy looking lamp, and you want to know things
that match that style. And now, Lens can help you. Or, if you see an outfit
that catches your eye, you can simply open the camera, tap on any item, and find out, of course, specific information like reviews, et cetera of any specific item, but you can also see all the things,
and browse around, that match that style. (applause) There’s two parts to it, of course. Lens has to search through
millions and millions of items, but we kind of know how to do that search. – (laughter)
– But the other part actually complicates things,
which is if they can be different textures, shapes, sizes, angles,
lighting conditions, et cetera. So, it’s a tough technical problem. But we’re making a lot of progress here
and really excited about it. So, the last thing
I want to tell you about today is how we’re making Lens work in real time. So, as you saw in the Style Match example, you start to see–you open the camera– and you start to see
Lens surface proactively all the information instantly. And it even anchors that information
to the things that you see. Now, this kind of thing– where it’s sifting through billions
of words, phrases, places, things, just in real time to give you what you need– not possible without machine learning. So, we’re using both on-device intelligence, but also tapping into the power
of cloud TPUs, which we announced last year at I/O,
to get this done. Really excited. And over time, what we want to do
is actually overlay the live results directly on top of things,
like store fronts, street signs, or a concert poster. So, you can simply point your phone
at a concert poster of Charlie Puth, and the music video just starts to play, just like that. This is an example of how the camera
is not just answering questions, but it is putting the answers
right where the questions are. And it’s very exciting. So, Smart Text Selection, Style Match, real time results– all coming to Lens in the next few weeks. Please check them out. (applause) So, those are some examples
of how Google is applying AI in Camera to get things done in the world around you. When it comes to applying AI,
mapping, and computer vision to solving problems in the real world, well, it doesn’t get more real
than self-driving cars. So, to tell you all about it, please join me in welcoming
the CEO of Waymo, John Krafcik. Thank you. (applause) ♪ (music) ♪ Hello, everyone! We’re so delighted to join our friends
at Google on stage here today. And while this is my first time at Shoreline, it actually isn’t the first time
for our self-driving cars. You see, back in 2009, in the parking lot just outside this theater, some of the very first tests
of self-driving technology took place. It was right here
where a group of Google engineers, roboticists, and researchers set out on a crazy mission to prove that cars
could actually drive themselves. Back then, most people thought
that self-driving cars were nothing more than science fiction. But this dedicated team of dreamers believed that self-driving vehicles
could make transportation safer, easier, and more accessible for everyone. And so, the Google
Self-Driving Car Project was born. Now, fast-forward to 2018, and the Google Self-Driving Car Project is now its own, independent
Alphabet company called Waymo. And we’ve moved
well beyond tinkering and research. Today, Waymo is the only company in the world with a fleet of fully self-driving cars, with no-one in the driver’s seat on public roads. Now, members of the public
in Phoenix, Arizona, have already started to experience some
of these fully self-driving rides, too. Let’s have a look. (man) Okay, Day One of self-driving.
Are you ready? Go! Oh, this is weird. (child laughing) This is the future. (laughing) Yeah, she was like,
“Is there no-one driving that car?” (woman laughing) I knew it! I was waiting for it. ♪ (music) ♪ (woman) You’d certainly never know that
there wasn’t someone driving this car. (man) Yo! Car! Selfie! Thank you, car. (giggles) Thank you, car. (applause) It’s pretty cool. All of these people are part of what
we call the Waymo Early Rider Program, where members of the public
use our self-driving cars in their daily lives. Over the last year, I’ve had a chance
to talk to some of these Early Riders and their stories
are actually pretty inspiring. One of our Early Riders, Neha, witnessed a tragic accident
when she was just a young teen, which scared her
into never getting her driver’s license. But now, she takes a Waymo to work every day. And there’s Jim and Barbara, who no longer have to worry
about losing their ability to get around as they grow older. Then, there’s the Jackson family. Waymo helps them all
navigate their jam-packed schedules, taking Kyla and Joseph to and from school, practices and meetups with friends. So, it’s not about science fiction. When we talk about
building self-driving technology, these are the people we’re building it for. In 2018, self-driving cars are already
transforming the way they live and move. So, Phoenix will be the first stop for Waymo’s Driverless
Transportation Service, which is launching later this year. Soon, everyone will be able
to call Waymo, using our app, and a fully self-driving car will pull up, with no-one in the driver’s seat, to whisk them away to their destination. And that’s just the beginning. Because, at Waymo, we’re not just building a better car. We’re building a better driver. And that driver can be used
in all kinds of applications– ride hailing, logistics, personal cars, connecting people to public transportation. And we see our technology as an enabler
for all of these different industries. And we intend to partner
with lots of different companies to make this self-driving future
a reality for everyone. Now, we can enable this future because of the breakthroughs
and investments we’ve made in AI. Back in those early days, Google was, perhaps,
the only company in the world investing in both AI
and self-driving technology at the same time. So, when Google started making
major advances in machine learning, with speech recognition, computer vision,
image search, and more– Waymo was in a unique position to benefit. For example, back in 2013, we were looking for a breakthrough technology to help us with pedestrian detection. Luckily for us, Google was already deploying
a new technique called deep learning, a type of machine learning that allows you
to create neural networks, with multiple layers,
to solve more complex problems. So, our self-driving engineers
teamed up with researchers from the Google Brain team, and within a matter of months we reduced the error rate
for detecting pedestrians by 100x. That’s right– not 100%, but a hundred times. – And today…
– (applause) Thanks. Today, AI plays an even greater role
in our self-driving system, unlocking our ability
to go truly self-driving. To tell you more
about how machine learning makes Waymo the safe and skilled driver
that you see on the road today, I’d like to introduce you to Dmitri. Thanks. ♪ (music) ♪ (applause) Good morning, everyone.
It’s great to be here. Now, at Waymo,
AI touches every part of our system, from perception to prediction
to decision-making to mapping, and so much more. To be a capable and safe driver, our cars need a deep semantic
understanding of the world around them. Our vehicles need to understand
and classify objects, interpret their movements,
reason about intent, and predict what they will do in the future. They need to understand how each object
interacts with everything else. And, finally, our cars need
to use all that information to act in a safe and predictable manner. So, needless to say, there’s a lot that goes
into building a self-driving car. And today I want to tell you about two areas where AI has made a huge impact– perception and prediction. So, first perception. Detecting and classifying objects
is a key part of driving. Pedestrians, in particular,
pose a unique challenge because they come in all kinds of shapes,
postures, and sizes. So, for example, here’s a construction worker peeking out of a manhole, with most of his body obscured. Here’s a pedestrian crossing the street,
concealed by a plank of wood. And here… we have pedestrians who are dressed
in inflatable dinosaur costumes. (laughter) Now, we haven’t taught our cars
about the Jurassic period, but can still classify them correctly. We can detect and classify these pedestrians because we apply deep nets to a combination of sensory data. Traditionally, in computer vision, neural networks are used
just in camera images and video. But our cars have a lot more
than just cameras. We also have lasers
to measure distance and shapes of objects, and radars to measure their speed. And, by applying machine learning
to this combination of sensor data, we can accurately detect pedestrians
in all forms, in real time. A second area where machine learning
has been incredibly powerful for Waymo is predicting how people
will behave on the road. Now, sometimes, people do
exactly what you expect them to, and, sometimes, they don’t. Take this example
of a car running a red light. Unfortunately, we see this kind of thing
more than we’d like. But let me break this down
from the car’s point of view. Our car is about to proceed
straight through an intersection. We have a clear green light, and cross traffic
is stopped with a red light. But, just as we enter the intersection, all the way in the right corner,
we see a vehicle coming fast. Our models understand
that this is unusual behavior for a vehicle that should be decelerating. We predict the car will run the red light. So, we preemptively slow down– which you can see here with this red fence– and this gives the red light runner
room to pass in front of us while it barely avoids
hitting another vehicle. We can detect this kind of anomaly because we’ve trained our ML models
using lots of examples. Today, our fleet has self-driven
more than 6 million miles on public roads, which means we’ve seen hundreds
of millions of real world interactions. To put that in perspective,
we drive more miles each day than the average American drives in a year. Now, it takes more than good algorithms to build a self-driving car. We also need really powerful infrastructure. And, at Waymo,
we use the TensorFlow ecosystem and Google’s data centers, including TPUs, to train our neural networks. And with TPUs, we can now train our nets up to 15 times more efficiently. We also use this powerful infrastructure to validate our models in simulation. And in this virtual world, we’re driving the equivalent of 25,000 cars all day, every day. All told, we’ve driven
more than 5 billion miles in simulation. And with this kind of scale, both in training
and validation of our models, we can quickly and efficiently
teach our cars new skills. And one skill we started to tackle is self-driving in difficult weather, such as snow, as you see here. (applause) And today, for the first time, I want to show you a behind-the-scenes look at what it’s like for our cars
to self-drive in snow. This is what our car sees
before we apply any filtering. (laughter) Driving in a snowstorm can be tough because snowflakes
can create a lot of noise for our sensors. But when we apply
machine learning to this data, this is what our car sees. We can clearly identify
each of these vehicles, even through all of the sensor noise. And the quicker we can unlock
these types of advanced capabilities, the quicker
we can bring our self-driving cars to more cities around the world, and to a city near you. We can’t wait to make our self-driving cars available to more people, moving us closer to a future where roads are safer, easier
and more accessible for everyone. Thanks, everyone. (applause) Now, please join me in welcoming back Jen to close out the morning session. ♪ (music) ♪ Thanks, Dmitri. It’s a great reminder of how AI
can play a role in helping people in new ways all the time. I started at Google as an engineering intern almost 19 years ago. And what struck me from almost
the very first day I walked in the door, was the commitment to push the boundaries and what was possible with technology, combined with a deep focus
on building products that had a real impact on people lives. And, as the years have passed,
I’ve seen, time and again, how technology
can play a really transformative role, from the earliest days
of things like Search and Maps, to new experiences,
like the Google Assistant. As I look at the Google of today,
I see those same early values alive and well. We continue to work hard, together with all of you, to build products for everyone, and products that matter. We constantly aspire
to raise the bar for ourselves even higher and to contribute to the world and to society in a responsible way. Now, we know
that to truly build for everyone, we need lots of perspectives in the mix. And so that’s why we broadened I/O this year to include an even wider range of voices. We’ve invited additional speakers
over the next three days to talk to you all about the broader role
that technology can play in everything
from promoting digital wellbeing, to empowering NGOs to achieve their missions, along with, of course, the hundreds of technical talks
that you’ve come to expect from us at I/O and that we hope
you can enjoy and learn from as well. Welcome to I/O 2018. Please enjoy, and I hope you all find
some inspiration in the next few days to keep building good things for everyone. Thank you. (applause) ♪ (electronic pop) ♪

, , , , , , , , , , , , , , , ,

Post navigation

Leave a Reply

Your email address will not be published. Required fields are marked *