0:00:00.832,0:00:05.657
For the next few minutes[br]I want to talk to you about...

0:00:05.657,0:00:09.122
or share with you a[br]breakthrough new approach

0:00:09.122,0:00:12.464
for managing items of[br]inventory inside of a warehouse.

0:00:12.464,0:00:15.022
We're talking about a Pick,[br]Pack and Ship setting here.

0:00:15.022,0:00:17.845
So as a hint,

0:00:17.845,0:00:21.998
this solution involves[br]hundreds of mobile robots,

0:00:21.998,0:00:24.422
sometimes thousands[br]of mobile robots,

0:00:24.422,0:00:27.020
moving around a warehouse.[br]And I'll get to the solution.

0:00:27.020,0:00:28.240
But for a moment, just think

0:00:28.240,0:00:30.766
about the last time [br]you ordered something online.

0:00:30.766,0:00:32.830
You were sitting[br]on your couch

0:00:32.830,0:00:36.890
and you decided that you[br]absolutely had to have this red t-shirt.

0:00:36.890,0:00:39.186
So click you put it[br]into your shopping cart.

0:00:39.186,0:00:41.084
And then you decided[br]that green pair of pants

0:00:41.084,0:00:42.982
looks pretty good too, click.

0:00:42.982,0:00:44.882
And maybe a blue[br]pair of shoes, click.

0:00:44.882,0:00:46.932
So at this point you've[br]assembled your order.

0:00:46.932,0:00:48.700
You didn't stop to think [br]for a moment that

0:00:48.700,0:00:50.468
that might not be a great outfit.

0:00:50.468,0:00:52.238
But you hit[br]Submit Order.

0:00:52.238,0:00:56.412
And two days later, this package[br]shows up on your doorstep.

0:00:56.412,0:00:59.366
And you open the box and like[br]Wow, there's my goo.

0:00:59.366,0:01:02.327
Did you ever stop to think about[br]how those items of inventory

0:01:02.327,0:01:06.540
actually found their way inside[br]that box in the warehouse?

0:01:06.540,0:01:08.938
So I'm here to tell you [br]it's that guy right there.

0:01:10.476,0:01:13.978
So deep in the[br]middle of that picture

0:01:13.978,0:01:16.493
you see a classic[br]Pick Pack Worker

0:01:16.493,0:01:19.718
in a distribution or[br]order fulfillments setting.

0:01:19.718,0:01:23.600
Classically these pick workers[br]will spend 60 to 70% of their day

0:01:23.600,0:01:25.512
wandering around[br]the warehouse.

0:01:25.512,0:01:28.223
They'll often walk[br]as much as 5, 10 miles

0:01:28.223,0:01:30.884
in pursuit of[br]those items of inventory.

0:01:30.884,0:01:35.305
Not only is this an[br]unproductive way to fill orders,

0:01:35.305,0:01:39.362
it also turns out to be an[br]unfulfilling way to fill orders.

0:01:39.362,0:01:42.993
So let me tell you where I[br]first bumped into this problem.

0:01:42.993,0:01:47.047
I was out in the Bay area [br]in 1999-2000, the dot com boom.

0:01:47.047,0:01:51.109
I worked for a fabulously[br]spectacular flame out called Webvan.

0:01:51.109,0:01:52.930
(Laughter)

0:01:52.930,0:01:55.660
This company raised hundreds of[br]millions of dollars with the notion that

0:01:55.660,0:01:58.442
we will deliver[br]grocery orders online.

0:01:58.442,0:02:02.615
And it really came down to the fact[br]that we couldn't do it cost effectively.

0:02:02.615,0:02:06.577
Turns out e-commerce was something[br]that was very hard and very costly.

0:02:06.577,0:02:10.828
In this particular instance we were trying[br]to assemble 30 items of inventory

0:02:10.828,0:02:14.800
into a few totes, onto a van[br]to deliver to the home.

0:02:14.800,0:02:18.600
And when you think about it,[br]it was costing us $30.

0:02:18.600,0:02:21.686
Imagine, we had an[br]89-cent can of soup

0:02:21.686,0:02:25.362
that was costing us $1 to[br]pick and pack into that tote.

0:02:25.362,0:02:28.570
And that's before we actually[br]tried to deliver it to the home.

0:02:28.570,0:02:31.357
So long story short,[br]during my 1-year at Webvan,

0:02:31.357,0:02:34.593
what I realized by talking to [br]all the material-handling providers

0:02:34.593,0:02:39.231
was that there was no solution designed[br]specifically to solve each base picking.

0:02:39.231,0:02:43.254
Red item, green, blue, getting[br]those 3 things in a box.

0:02:43.254,0:02:46.239
So we said, you know, there's just[br]got to be a better way to do this.

0:02:46.239,0:02:48.766
Existing material handling[br]was setup to pump

0:02:48.766,0:02:52.533
pallets and cases of[br]goo to retail stores.

0:02:52.533,0:02:56.330
Of course Webvan went out of business[br]and about a year and a half later,

0:02:56.330,0:02:59.910
I was still noodling on this problem.[br]It was still nagging at me.

0:02:59.910,0:03:01.778
And I started[br]thinking about it again.

0:03:01.778,0:03:06.905
And I said "Let me just focus briefly[br]on what I wanted as a pick worker."

0:03:06.905,0:03:09.236
What my vision for[br]how it should work.

0:03:09.236,0:03:10.650
(Laughter)

0:03:10.650,0:03:12.572
I said "let's focus[br]on the problem."

0:03:12.572,0:03:16.427
I have an order here and what[br]I want to do is I want to put

0:03:16.427,0:03:18.647
red, green and blue[br]in this box right here.

0:03:18.647,0:03:21.499
What I need is a system where I put out[br]my hand and poof!

0:03:21.499,0:03:24.022
the product shows up [br]and I pack it into the order,

0:03:24.022,0:03:25.715
and now we're thinking,

0:03:25.715,0:03:29.729
"this would be a very operator-centric[br]approach to solving the problem.

0:03:29.729,0:03:33.956
This is what I need. What technology[br]is available to solve this problem?"

0:03:33.956,0:03:37.897
But as you can see, orders can come[br]and go, product can come and go.

0:03:37.897,0:03:42.580
It allows us to focus on making the[br]pick worker the center of the problem,

0:03:42.580,0:03:47.204
and providing them the tools to make[br]them as productive as possible.

0:03:47.204,0:03:49.304
So how did I[br]arrive at this notion?

0:03:49.304,0:03:52.837
Well, actually it came from[br]a brainstorming exercise,

0:03:52.837,0:03:55.677
probably a technique[br]that many of you use,

0:03:55.677,0:03:57.833
It's this notion of[br]testing your ideas.

0:03:57.833,0:03:59.563
Take a blank sheet of course,

0:03:59.563,0:04:03.593
but then test your ideas[br]at the limits. Infinity, zero...

0:04:03.593,0:04:06.775
In this particular case, we[br]challenged ourselves with the idea:

0:04:06.775,0:04:09.751
wWhat if we had to build a[br]distribution center in China,

0:04:09.751,0:04:12.365
where it's a very,[br]very low cost market?

0:04:12.365,0:04:15.578
And say, labor is cheap,[br]land is cheap.

0:04:15.578,0:04:17.224
And we said specificall:

0:04:17.224,0:04:20.230
"what if it was zero dollars[br]an hour for direct labor

0:04:20.230,0:04:22.946
and we could build a million[br]square foot distribution center?"

0:04:22.946,0:04:25.021
So naturally that[br]led to ideas that said:

0:04:25.021,0:04:26.829
"Let's put lots of people[br]in the warehouse."

0:04:26.829,0:04:29.374
And I said: "hold on,[br]zero dollars per hour,

0:04:29.374,0:04:32.231
what I would do is "hire"

0:04:32.231,0:04:36.358
10,000 workers to come to the[br]warehouse every morning at 8:00 am,

0:04:36.358,0:04:39.477
walk into the warehouse and[br]pickup 1 item of inventory

0:04:39.477,0:04:41.210
and then just stand there.

0:04:41.210,0:04:43.749
So you hold Captain Crunch,[br]you hold the Mountain Dew,

0:04:43.749,0:04:45.172
you hold the Diet Coke.

0:04:45.172,0:04:47.428
If I need it, I'll call you,[br]otherwise just stand there.

0:04:47.428,0:04:50.815
But when I need Diet Coke and I call[br]you guys talk amongst yourselves,

0:04:50.815,0:04:54.936
Diet Coke walks up to the front,[br]pick it, put it in the tote, away it goes."

0:04:54.936,0:04:59.588
Like wow, what if the products[br]could walk and talk on their own?

0:04:59.588,0:05:01.926
That's a very interesting[br]very powerful way

0:05:01.926,0:05:04.520
that we could potentially[br]organize this warehouse.

0:05:04.520,0:05:06.868
So of course,[br]labor isn't free,

0:05:06.868,0:05:10.176
on that practical[br]versus awesome spectrum.

0:05:10.176,0:05:11.866
(Laughter)

0:05:11.866,0:05:14.983
So we said mobile shelving.[br]We'll put them on mobile shelving.

0:05:14.983,0:05:19.776
We'll use mobile robots and[br]we'll move the inventory around.

0:05:19.776,0:05:24.194
And so we got underway on that and[br]then I'm sitting on my couch in 2008.

0:05:24.194,0:05:28.013
Did any of you see the Beijing[br]Olympics, the opening ceremonies?

0:05:28.013,0:05:31.054
I about fell out of my[br]couch when I saw this.

0:05:31.054,0:05:32.527
I'm like, that was the idea!

0:05:32.527,0:05:37.026
(Laughter and Applause)

0:05:37.026,0:05:40.917
We'll put thousands of people on[br]the warehouse floor, the stadium floor.

0:05:40.917,0:05:44.952
But interesting enough, this[br]actually relates to the idea

0:05:44.952,0:05:50.364
in that these guys were creating some[br]incredibly powerful impressive digital art,

0:05:50.364,0:05:52.440
all without computers,[br]I'm told,

0:05:52.440,0:05:54.886
it was all peer-to-peer[br]coordination and communication.

0:05:54.886,0:05:56.462
You stand up,[br]I'll squat down.

0:05:56.462,0:05:58.107
And they made[br]some fabulous art.

0:05:58.107,0:06:00.795
It speaks to the[br]power of emergence

0:06:00.795,0:06:04.763
in systems when you let things[br]start to talk with each other.

0:06:04.763,0:06:08.541
So that was a little[br]bit of the journey.

0:06:08.541,0:06:12.579
So of course, now what became[br]of the practical reality of this idea?

0:06:12.579,0:06:14.385
Here is a warehouse.

0:06:14.385,0:06:18.161
It's a pick, pack and ship center[br]that has about 10,000 different SKU's.

0:06:18.161,0:06:22.298
We'll call them red pens,[br]green pens, yellow Post-It Notes.

0:06:22.298,0:06:25.677
We send the little orange robots[br]out to pick up the blue shelving pods.

0:06:25.677,0:06:27.845
And we deliver them[br]to the side of the building.

0:06:27.845,0:06:30.981
So all the pick workers now[br]get to stay on the perimeter.

0:06:30.981,0:06:33.323
And the game here is[br]to pick up the shelves,

0:06:33.323,0:06:36.647
take them down the highway and[br]deliver them straight to the pick worker.

0:06:36.647,0:06:38.784
This pick worker's life[br]is completely different.

0:06:38.784,0:06:42.201
Rather than wandering around[br]the warehouse, she gets to stay still

0:06:42.201,0:06:43.789
in a pick station like this

0:06:43.789,0:06:47.787
and every product in the[br]building can now come to her.

0:06:47.787,0:06:51.065
So the process[br]is very productive.

0:06:51.065,0:06:55.260
Reach in, pick an item,[br]scan the bar code, pack it out.

0:06:55.260,0:06:56.909
By the time[br]you turn around,

0:06:56.909,0:06:59.948
there's another product there[br]ready to be picked and packed.

0:06:59.948,0:07:02.958
So what we've done is take[br]out all of the non-value added

0:07:02.958,0:07:05.642
walking, searching,[br]wasting, waited time,

0:07:05.642,0:07:09.920
and we've developed a very [br]high-fidelity way to pick these orders,

0:07:09.920,0:07:14.084
where you point at it with[br]a laser, scan UPC barcode,

0:07:14.084,0:07:17.278
and then indicate with a light[br]which box it needs to go into.

0:07:17.278,0:07:20.764
So more productive, more[br]accurate and it turns out

0:07:20.764,0:07:25.070
it's a more interesting office[br]environment for these pick workers.

0:07:25.070,0:07:27.507
They actually complete[br]the whole order.

0:07:27.507,0:07:30.034
So they do red, green and blue[br]not just a part of the order.

0:07:30.034,0:07:33.648
And they feel a little bit more[br]in control of their environment.

0:07:33.648,0:07:36.846
So the side effects[br]of this approach

0:07:36.846,0:07:38.414
are what really surprised us.

0:07:38.414,0:07:39.992
We knew it was going [br]to be more productive.

0:07:39.992,0:07:44.062
But we didn't realize just how[br]pervasive this way of thinking

0:07:44.062,0:07:49.292
extended to other[br]functions in the warehouse.

0:07:49.292,0:07:54.124
But what effectively this approach[br]is doing inside of the DC

0:07:54.124,0:07:58.588
is turning it into a massively[br]parallel processing engine.

0:07:58.588,0:08:01.211
So this is again a[br]cross fertilization of ideas.

0:08:01.211,0:08:03.150
Here's a warehouse[br]and we're thinking about

0:08:03.150,0:08:06.669
parallel processing[br]supercomputer architectures.

0:08:06.669,0:08:09.066
The notion here is that you have

0:08:09.066,0:08:11.863
10 workers on [br]the right side of the screen

0:08:11.863,0:08:16.111
that are now all independent[br]autonomous pick workers.

0:08:16.111,0:08:20.015
If the worker in station 3 decides[br]to leave and go to the bathroom,

0:08:20.015,0:08:23.499
it has no impact on the[br]productivity of the other 9 workers.

0:08:23.499,0:08:27.869
Contrast that, for a moment, with the[br]traditional method of using a conveyor.

0:08:27.869,0:08:29.928
When one person[br]passes the order to you,

0:08:29.928,0:08:32.427
you put something in[br]and pass it downstream.

0:08:32.427,0:08:35.544
Everyone has to be in place[br]for that serial process to work.

0:08:35.544,0:08:38.721
This becomes a more robust[br]way to think about the warehouse.

0:08:38.721,0:08:43.265
And underneath the hoods gets[br]interesting in that we're tracking

0:08:43.265,0:08:45.003
the popularity[br]of the products.

0:08:45.003,0:08:47.827
And we're using dynamic[br]and adaptive algorithms

0:08:47.827,0:08:52.281
to tune the floor[br]of the warehouse.

0:08:52.281,0:08:57.165
So what you see here potentially[br]the week leading up to Valentines' Day.

0:08:57.165,0:09:01.008
All that pink chalky candy has[br]moved to the front on the building

0:09:01.008,0:09:04.901
and is now being picked into a[br]lot of orders in those pick stations.

0:09:04.901,0:09:09.064
Come in two days after Valentine's Day[br]and that candy, the leftover candy,

0:09:09.064,0:09:11.337
has all drifted to the[br]back of the warehouse

0:09:11.337,0:09:15.630
and is occupying the cooler[br]zone on the thermo map there.

0:09:15.630,0:09:19.113
One other side effect of this[br]approach using the parallel processing

0:09:19.113,0:09:22.108
is these things can[br]scale to ginormous.

0:09:22.108,0:09:23.635
(Laughter)

0:09:23.635,0:09:26.369
So whether you(re doing[br]2 pick stations, 20 pick stations, or

0:09:26.369,0:09:29.642
200 pick stations, the[br]path planning algorithms

0:09:29.642,0:09:32.185
and all of the inventory[br]algorithms just work.

0:09:32.185,0:09:36.541
In this example you[br]see that the inventory

0:09:36.541,0:09:38.867
has now occupied all the[br]perimeter of the building

0:09:38.867,0:09:41.213
because that's where[br]the pick stations were.

0:09:41.213,0:09:43.231
They sorted it[br]out for themselves.

0:09:43.231,0:09:45.518
So I'll conclude with[br]just one final video

0:09:45.518,0:09:48.502
that shows how[br]this comes to bear

0:09:48.502,0:09:52.096
on the pick worker's actual[br]kind of day in the life of.

0:09:52.096,0:09:56.432
So as we mentioned, the process is[br]to move inventory along the highway

0:09:56.432,0:09:59.084
and then find your way[br]into these pick stations.

0:09:59.084,0:10:01.555
And our software in the background

0:10:01.555,0:10:04.306
understands what's going on [br]in each station,

0:10:04.306,0:10:06.917
we direct deposit[br]across the highway

0:10:06.917,0:10:09.631
and we're attempting to[br]get into a queuing system

0:10:09.631,0:10:12.515
to present the work[br]to the pick worker.

0:10:12.515,0:10:15.760
What's interesting is we can even[br]adapt the speed of the pick workers.

0:10:15.760,0:10:19.686
The faster pickers get more pods[br]and the slower pickers get few.

0:10:19.686,0:10:22.824
But this pick worker now is[br]literally having that experience

0:10:22.824,0:10:24.677
that we described before.

0:10:24.677,0:10:27.221
She puts out her hand.[br]The product jumps into it.

0:10:27.221,0:10:29.426
Or she has to reach in and get it.

0:10:29.426,0:10:31.871
She scans it and [br]she puts it in the bucket.

0:10:31.871,0:10:35.667
And all of the rest of the technology[br]is kind of behind the scenes.

0:10:35.667,0:10:39.528
So she gets to now focus on the[br]picking and packing portion of her job.

0:10:39.528,0:10:42.802
Never has any idle time,[br]never has to leave her matt.

0:10:42.802,0:10:46.942
And actually we think[br]not only a more productive

0:10:46.942,0:10:50.212
and more accurate[br]way to fill orders.

0:10:50.212,0:10:53.622
We think it is a more[br]fulfilling way to fill orders.

0:10:53.622,0:10:56.830
The reason we can say[br]that though is that workers

0:10:56.830,0:10:58.972
in a lot of these[br]buildings now compete

0:10:58.972,0:11:02.154
for the privilege of working[br]in the KIVA zone that day.

0:11:02.154,0:11:04.817
And sometimes we'll catch[br]them on testimonial videos

0:11:04.817,0:11:06.934
saying such things as,

0:11:06.934,0:11:11.180
they have more energy after the[br]day to play with their grandchildren,

0:11:11.180,0:11:15.776
or in one case a guy said, "the[br]KIVA zone is so stress-free

0:11:15.776,0:11:18.891
that I've actually stopped taking[br]my blood pressure medication."

0:11:18.891,0:11:20.725
(Laughter)

0:11:20.725,0:11:24.724
That was at a pharmaceutical distributor.[br]So they told us not to use that video.

0:11:24.724,0:11:28.292
(Laughter)

0:11:28.292,0:11:31.316
So what I wanted to leave you[br]with today is the notion that

0:11:31.316,0:11:34.171
when you let things start[br]to kind of think and walk

0:11:34.171,0:11:39.462
and talk on their own, interesting[br]processes and productivities can emerge.

0:11:39.462,0:11:42.403
And now I think next time[br]you go to your front step

0:11:42.403,0:11:44.914
and pick up that box that[br]you just ordered online,

0:11:44.914,0:11:47.138
you break it open and[br]the goo is in there,

0:11:47.138,0:11:49.891
you'll have some wonderment[br]as to whether a robot

0:11:49.891,0:11:52.484
assisted in the picking[br]and packing of that order.

0:11:52.484,0:11:54.163
Thank you

0:11:54.163,0:11:58.793
(Applause)