1
00:00:00,832 --> 00:00:05,657
For the next few minutes
I want to talk to you about...

2
00:00:05,657 --> 00:00:09,122
or share with you a
breakthrough new approach

3
00:00:09,122 --> 00:00:12,464
for managing items of
inventory inside of a warehouse.

4
00:00:12,464 --> 00:00:15,022
We're talking about a Pick,
Pack and Ship setting here.

5
00:00:15,022 --> 00:00:17,845
So as a hint,

6
00:00:17,845 --> 00:00:21,998
this solution involves
hundreds of mobile robots,

7
00:00:21,998 --> 00:00:24,422
sometimes thousands
of mobile robots,

8
00:00:24,422 --> 00:00:27,020
moving around a warehouse.
And I'll get to the solution.

9
00:00:27,020 --> 00:00:28,240
But for a moment, just think

10
00:00:28,240 --> 00:00:30,766
about the last time 
you ordered something online.

11
00:00:30,766 --> 00:00:32,830
You were sitting
on your couch

12
00:00:32,830 --> 00:00:36,890
and you decided that you
absolutely had to have this red t-shirt.

13
00:00:36,890 --> 00:00:39,186
So click you put it
into your shopping cart.

14
00:00:39,186 --> 00:00:41,084
And then you decided
that green pair of pants

15
00:00:41,084 --> 00:00:42,982
looks pretty good too, click.

16
00:00:42,982 --> 00:00:44,882
And maybe a blue
pair of shoes, click.

17
00:00:44,882 --> 00:00:46,932
So at this point you've
assembled your order.

18
00:00:46,932 --> 00:00:48,700
You didn't stop to think 
for a moment that

19
00:00:48,700 --> 00:00:50,468
that might not be a great outfit.

20
00:00:50,468 --> 00:00:52,238
But you hit
Submit Order.

21
00:00:52,238 --> 00:00:56,412
And two days later, this package
shows up on your doorstep.

22
00:00:56,412 --> 00:00:59,366
And you open the box and like
Wow, there's my goo.

23
00:00:59,366 --> 00:01:02,327
Did you ever stop to think about
how those items of inventory

24
00:01:02,327 --> 00:01:06,540
actually found their way inside
that box in the warehouse?

25
00:01:06,540 --> 00:01:08,938
So I'm here to tell you 
it's that guy right there.

26
00:01:10,476 --> 00:01:13,978
So deep in the
middle of that picture

27
00:01:13,978 --> 00:01:16,493
you see a classic
Pick Pack Worker

28
00:01:16,493 --> 00:01:19,718
in a distribution or
order fulfillments setting.

29
00:01:19,718 --> 00:01:23,600
Classically these pick workers
will spend 60 to 70% of their day

30
00:01:23,600 --> 00:01:25,512
wandering around
the warehouse.

31
00:01:25,512 --> 00:01:28,223
They'll often walk
as much as 5, 10 miles

32
00:01:28,223 --> 00:01:30,884
in pursuit of
those items of inventory.

33
00:01:30,884 --> 00:01:35,305
Not only is this an
unproductive way to fill orders,

34
00:01:35,305 --> 00:01:39,362
it also turns out to be an
unfulfilling way to fill orders.

35
00:01:39,362 --> 00:01:42,993
So let me tell you where I
first bumped into this problem.

36
00:01:42,993 --> 00:01:47,047
I was out in the Bay area 
in 1999-2000, the dot com boom.

37
00:01:47,047 --> 00:01:51,109
I worked for a fabulously
spectacular flame out called Webvan.

38
00:01:51,109 --> 00:01:52,930
(Laughter)

39
00:01:52,930 --> 00:01:55,660
This company raised hundreds of
millions of dollars with the notion that

40
00:01:55,660 --> 00:01:58,442
we will deliver
grocery orders online.

41
00:01:58,442 --> 00:02:02,615
And it really came down to the fact
that we couldn't do it cost effectively.

42
00:02:02,615 --> 00:02:06,577
Turns out e-commerce was something
that was very hard and very costly.

43
00:02:06,577 --> 00:02:10,828
In this particular instance we were trying
to assemble 30 items of inventory

44
00:02:10,828 --> 00:02:14,800
into a few totes, onto a van
to deliver to the home.

45
00:02:14,800 --> 00:02:18,600
And when you think about it,
it was costing us $30.

46
00:02:18,600 --> 00:02:21,686
Imagine, we had an
89-cent can of soup

47
00:02:21,686 --> 00:02:25,362
that was costing us $1 to
pick and pack into that tote.

48
00:02:25,362 --> 00:02:28,570
And that's before we actually
tried to deliver it to the home.

49
00:02:28,570 --> 00:02:31,357
So long story short,
during my 1-year at Webvan,

50
00:02:31,357 --> 00:02:34,593
what I realized by talking to 
all the material-handling providers

51
00:02:34,593 --> 00:02:39,231
was that there was no solution designed
specifically to solve each base picking.

52
00:02:39,231 --> 00:02:43,254
Red item, green, blue, getting
those 3 things in a box.

53
00:02:43,254 --> 00:02:46,239
So we said, you know, there's just
got to be a better way to do this.

54
00:02:46,239 --> 00:02:48,766
Existing material handling
was setup to pump

55
00:02:48,766 --> 00:02:52,533
pallets and cases of
goo to retail stores.

56
00:02:52,533 --> 00:02:56,330
Of course Webvan went out of business
and about a year and a half later,

57
00:02:56,330 --> 00:02:59,910
I was still noodling on this problem.
It was still nagging at me.

58
00:02:59,910 --> 00:03:01,778
And I started
thinking about it again.

59
00:03:01,778 --> 00:03:06,905
And I said "Let me just focus briefly
on what I wanted as a pick worker."

60
00:03:06,905 --> 00:03:09,236
What my vision for
how it should work.

61
00:03:09,236 --> 00:03:10,650
(Laughter)

62
00:03:10,650 --> 00:03:12,572
I said "let's focus
on the problem."

63
00:03:12,572 --> 00:03:16,427
I have an order here and what
I want to do is I want to put

64
00:03:16,427 --> 00:03:18,647
red, green and blue
in this box right here.

65
00:03:18,647 --> 00:03:21,499
What I need is a system where I put out
my hand and poof!

66
00:03:21,499 --> 00:03:24,022
the product shows up 
and I pack it into the order,

67
00:03:24,022 --> 00:03:25,715
and now we're thinking,

68
00:03:25,715 --> 00:03:29,729
"this would be a very operator-centric
approach to solving the problem.

69
00:03:29,729 --> 00:03:33,956
This is what I need. What technology
is available to solve this problem?"

70
00:03:33,956 --> 00:03:37,897
But as you can see, orders can come
and go, product can come and go.

71
00:03:37,897 --> 00:03:42,580
It allows us to focus on making the
pick worker the center of the problem,

72
00:03:42,580 --> 00:03:47,204
and providing them the tools to make
them as productive as possible.

73
00:03:47,204 --> 00:03:49,304
So how did I
arrive at this notion?

74
00:03:49,304 --> 00:03:52,837
Well, actually it came from
a brainstorming exercise,

75
00:03:52,837 --> 00:03:55,677
probably a technique
that many of you use,

76
00:03:55,677 --> 00:03:57,833
It's this notion of
testing your ideas.

77
00:03:57,833 --> 00:03:59,563
Take a blank sheet of course,

78
00:03:59,563 --> 00:04:03,593
but then test your ideas
at the limits. Infinity, zero...

79
00:04:03,593 --> 00:04:06,775
In this particular case, we
challenged ourselves with the idea:

80
00:04:06,775 --> 00:04:09,751
wWhat if we had to build a
distribution center in China,

81
00:04:09,751 --> 00:04:12,365
where it's a very,
very low cost market?

82
00:04:12,365 --> 00:04:15,578
And say, labor is cheap,
land is cheap.

83
00:04:15,578 --> 00:04:17,224
And we said specificall:

84
00:04:17,224 --> 00:04:20,230
"what if it was zero dollars
an hour for direct labor

85
00:04:20,230 --> 00:04:22,946
and we could build a million
square foot distribution center?"

86
00:04:22,946 --> 00:04:25,021
So naturally that
led to ideas that said:

87
00:04:25,021 --> 00:04:26,829
"Let's put lots of people
in the warehouse."

88
00:04:26,829 --> 00:04:29,374
And I said: "hold on,
zero dollars per hour,

89
00:04:29,374 --> 00:04:32,231
what I would do is "hire"

90
00:04:32,231 --> 00:04:36,358
10,000 workers to come to the
warehouse every morning at 8:00 am,

91
00:04:36,358 --> 00:04:39,477
walk into the warehouse and
pickup 1 item of inventory

92
00:04:39,477 --> 00:04:41,210
and then just stand there.

93
00:04:41,210 --> 00:04:43,749
So you hold Captain Crunch,
you hold the Mountain Dew,

94
00:04:43,749 --> 00:04:45,172
you hold the Diet Coke.

95
00:04:45,172 --> 00:04:47,428
If I need it, I'll call you,
otherwise just stand there.

96
00:04:47,428 --> 00:04:50,815
But when I need Diet Coke and I call
you guys talk amongst yourselves,

97
00:04:50,815 --> 00:04:54,936
Diet Coke walks up to the front,
pick it, put it in the tote, away it goes."

98
00:04:54,936 --> 00:04:59,588
Like wow, what if the products
could walk and talk on their own?

99
00:04:59,588 --> 00:05:01,926
That's a very interesting
very powerful way

100
00:05:01,926 --> 00:05:04,520
that we could potentially
organize this warehouse.

101
00:05:04,520 --> 00:05:06,868
So of course,
labor isn't free,

102
00:05:06,868 --> 00:05:10,176
on that practical
versus awesome spectrum.

103
00:05:10,176 --> 00:05:11,866
(Laughter)

104
00:05:11,866 --> 00:05:14,983
So we said mobile shelving.
We'll put them on mobile shelving.

105
00:05:14,983 --> 00:05:19,776
We'll use mobile robots and
we'll move the inventory around.

106
00:05:19,776 --> 00:05:24,194
And so we got underway on that and
then I'm sitting on my couch in 2008.

107
00:05:24,194 --> 00:05:28,013
Did any of you see the Beijing
Olympics, the opening ceremonies?

108
00:05:28,013 --> 00:05:31,054
I about fell out of my
couch when I saw this.

109
00:05:31,054 --> 00:05:32,527
I'm like, that was the idea!

110
00:05:32,527 --> 00:05:37,026
(Laughter and Applause)

111
00:05:37,026 --> 00:05:40,917
We'll put thousands of people on
the warehouse floor, the stadium floor.

112
00:05:40,917 --> 00:05:44,952
But interesting enough, this
actually relates to the idea

113
00:05:44,952 --> 00:05:50,364
in that these guys were creating some
incredibly powerful impressive digital art,

114
00:05:50,364 --> 00:05:52,440
all without computers,
I'm told,

115
00:05:52,440 --> 00:05:54,886
it was all peer-to-peer
coordination and communication.

116
00:05:54,886 --> 00:05:56,462
You stand up,
I'll squat down.

117
00:05:56,462 --> 00:05:58,107
And they made
some fabulous art.

118
00:05:58,107 --> 00:06:00,795
It speaks to the
power of emergence

119
00:06:00,795 --> 00:06:04,763
in systems when you let things
start to talk with each other.

120
00:06:04,763 --> 00:06:08,541
So that was a little
bit of the journey.

121
00:06:08,541 --> 00:06:12,579
So of course, now what became
of the practical reality of this idea?

122
00:06:12,579 --> 00:06:14,385
Here is a warehouse.

123
00:06:14,385 --> 00:06:18,161
It's a pick, pack and ship center
that has about 10,000 different SKU's.

124
00:06:18,161 --> 00:06:22,298
We'll call them red pens,
green pens, yellow Post-It Notes.

125
00:06:22,298 --> 00:06:25,677
We send the little orange robots
out to pick up the blue shelving pods.

126
00:06:25,677 --> 00:06:27,845
And we deliver them
to the side of the building.

127
00:06:27,845 --> 00:06:30,981
So all the pick workers now
get to stay on the perimeter.

128
00:06:30,981 --> 00:06:33,323
And the game here is
to pick up the shelves,

129
00:06:33,323 --> 00:06:36,647
take them down the highway and
deliver them straight to the pick worker.

130
00:06:36,647 --> 00:06:38,784
This pick worker's life
is completely different.

131
00:06:38,784 --> 00:06:42,201
Rather than wandering around
the warehouse, she gets to stay still

132
00:06:42,201 --> 00:06:43,789
in a pick station like this

133
00:06:43,789 --> 00:06:47,787
and every product in the
building can now come to her.

134
00:06:47,787 --> 00:06:51,065
So the process
is very productive.

135
00:06:51,065 --> 00:06:55,260
Reach in, pick an item,
scan the bar code, pack it out.

136
00:06:55,260 --> 00:06:56,909
By the time
you turn around,

137
00:06:56,909 --> 00:06:59,948
there's another product there
ready to be picked and packed.

138
00:06:59,948 --> 00:07:02,958
So what we've done is take
out all of the non-value added

139
00:07:02,958 --> 00:07:05,642
walking, searching,
wasting, waited time,

140
00:07:05,642 --> 00:07:09,920
and we've developed a very 
high-fidelity way to pick these orders,

141
00:07:09,920 --> 00:07:14,084
where you point at it with
a laser, scan UPC barcode,

142
00:07:14,084 --> 00:07:17,278
and then indicate with a light
which box it needs to go into.

143
00:07:17,278 --> 00:07:20,764
So more productive, more
accurate and it turns out

144
00:07:20,764 --> 00:07:25,070
it's a more interesting office
environment for these pick workers.

145
00:07:25,070 --> 00:07:27,507
They actually complete
the whole order.

146
00:07:27,507 --> 00:07:30,034
So they do red, green and blue
not just a part of the order.

147
00:07:30,034 --> 00:07:33,648
And they feel a little bit more
in control of their environment.

148
00:07:33,648 --> 00:07:36,846
So the side effects
of this approach

149
00:07:36,846 --> 00:07:38,414
are what really surprised us.

150
00:07:38,414 --> 00:07:39,992
We knew it was going 
to be more productive.

151
00:07:39,992 --> 00:07:44,062
But we didn't realize just how
pervasive this way of thinking

152
00:07:44,062 --> 00:07:49,292
extended to other
functions in the warehouse.

153
00:07:49,292 --> 00:07:54,124
But what effectively this approach
is doing inside of the DC

154
00:07:54,124 --> 00:07:58,588
is turning it into a massively
parallel processing engine.

155
00:07:58,588 --> 00:08:01,211
So this is again a
cross fertilization of ideas.

156
00:08:01,211 --> 00:08:03,150
Here's a warehouse
and we're thinking about

157
00:08:03,150 --> 00:08:06,669
parallel processing
supercomputer architectures.

158
00:08:06,669 --> 00:08:09,066
The notion here is that you have

159
00:08:09,066 --> 00:08:11,863
10 workers on 
the right side of the screen

160
00:08:11,863 --> 00:08:16,111
that are now all independent
autonomous pick workers.

161
00:08:16,111 --> 00:08:20,015
If the worker in station 3 decides
to leave and go to the bathroom,

162
00:08:20,015 --> 00:08:23,499
it has no impact on the
productivity of the other 9 workers.

163
00:08:23,499 --> 00:08:27,869
Contrast that, for a moment, with the
traditional method of using a conveyor.

164
00:08:27,869 --> 00:08:29,928
When one person
passes the order to you,

165
00:08:29,928 --> 00:08:32,427
you put something in
and pass it downstream.

166
00:08:32,427 --> 00:08:35,544
Everyone has to be in place
for that serial process to work.

167
00:08:35,544 --> 00:08:38,721
This becomes a more robust
way to think about the warehouse.

168
00:08:38,721 --> 00:08:43,265
And underneath the hoods gets
interesting in that we're tracking

169
00:08:43,265 --> 00:08:45,003
the popularity
of the products.

170
00:08:45,003 --> 00:08:47,827
And we're using dynamic
and adaptive algorithms

171
00:08:47,827 --> 00:08:52,281
to tune the floor
of the warehouse.

172
00:08:52,281 --> 00:08:57,165
So what you see here potentially
the week leading up to Valentines' Day.

173
00:08:57,165 --> 00:09:01,008
All that pink chalky candy has
moved to the front on the building

174
00:09:01,008 --> 00:09:04,901
and is now being picked into a
lot of orders in those pick stations.

175
00:09:04,901 --> 00:09:09,064
Come in two days after Valentine's Day
and that candy, the leftover candy,

176
00:09:09,064 --> 00:09:11,337
has all drifted to the
back of the warehouse

177
00:09:11,337 --> 00:09:15,630
and is occupying the cooler
zone on the thermo map there.

178
00:09:15,630 --> 00:09:19,113
One other side effect of this
approach using the parallel processing

179
00:09:19,113 --> 00:09:22,108
is these things can
scale to ginormous.

180
00:09:22,108 --> 00:09:23,635
(Laughter)

181
00:09:23,635 --> 00:09:26,369
So whether you(re doing
2 pick stations, 20 pick stations, or

182
00:09:26,369 --> 00:09:29,642
200 pick stations, the
path planning algorithms

183
00:09:29,642 --> 00:09:32,185
and all of the inventory
algorithms just work.

184
00:09:32,185 --> 00:09:36,541
In this example you
see that the inventory

185
00:09:36,541 --> 00:09:38,867
has now occupied all the
perimeter of the building

186
00:09:38,867 --> 00:09:41,213
because that's where
the pick stations were.

187
00:09:41,213 --> 00:09:43,231
They sorted it
out for themselves.

188
00:09:43,231 --> 00:09:45,518
So I'll conclude with
just one final video

189
00:09:45,518 --> 00:09:48,502
that shows how
this comes to bear

190
00:09:48,502 --> 00:09:52,096
on the pick worker's actual
kind of day in the life of.

191
00:09:52,096 --> 00:09:56,432
So as we mentioned, the process is
to move inventory along the highway

192
00:09:56,432 --> 00:09:59,084
and then find your way
into these pick stations.

193
00:09:59,084 --> 00:10:01,555
And our software in the background

194
00:10:01,555 --> 00:10:04,306
understands what's going on 
in each station,

195
00:10:04,306 --> 00:10:06,917
we direct deposit
across the highway

196
00:10:06,917 --> 00:10:09,631
and we're attempting to
get into a queuing system

197
00:10:09,631 --> 00:10:12,515
to present the work
to the pick worker.

198
00:10:12,515 --> 00:10:15,760
What's interesting is we can even
adapt the speed of the pick workers.

199
00:10:15,760 --> 00:10:19,686
The faster pickers get more pods
and the slower pickers get few.

200
00:10:19,686 --> 00:10:22,824
But this pick worker now is
literally having that experience

201
00:10:22,824 --> 00:10:24,677
that we described before.

202
00:10:24,677 --> 00:10:27,221
She puts out her hand.
The product jumps into it.

203
00:10:27,221 --> 00:10:29,426
Or she has to reach in and get it.

204
00:10:29,426 --> 00:10:31,871
She scans it and 
she puts it in the bucket.

205
00:10:31,871 --> 00:10:35,667
And all of the rest of the technology
is kind of behind the scenes.

206
00:10:35,667 --> 00:10:39,528
So she gets to now focus on the
picking and packing portion of her job.

207
00:10:39,528 --> 00:10:42,802
Never has any idle time,
never has to leave her matt.

208
00:10:42,802 --> 00:10:46,942
And actually we think
not only a more productive

209
00:10:46,942 --> 00:10:50,212
and more accurate
way to fill orders.

210
00:10:50,212 --> 00:10:53,622
We think it is a more
fulfilling way to fill orders.

211
00:10:53,622 --> 00:10:56,830
The reason we can say
that though is that workers

212
00:10:56,830 --> 00:10:58,972
in a lot of these
buildings now compete

213
00:10:58,972 --> 00:11:02,154
for the privilege of working
in the KIVA zone that day.

214
00:11:02,154 --> 00:11:04,817
And sometimes we'll catch
them on testimonial videos

215
00:11:04,817 --> 00:11:06,934
saying such things as,

216
00:11:06,934 --> 00:11:11,180
they have more energy after the
day to play with their grandchildren,

217
00:11:11,180 --> 00:11:15,776
or in one case a guy said, "the
KIVA zone is so stress-free

218
00:11:15,776 --> 00:11:18,891
that I've actually stopped taking
my blood pressure medication."

219
00:11:18,891 --> 00:11:20,725
(Laughter)

220
00:11:20,725 --> 00:11:24,724
That was at a pharmaceutical distributor.
So they told us not to use that video.

221
00:11:24,724 --> 00:11:28,292
(Laughter)

222
00:11:28,292 --> 00:11:31,316
So what I wanted to leave you
with today is the notion that

223
00:11:31,316 --> 00:11:34,171
when you let things start
to kind of think and walk

224
00:11:34,171 --> 00:11:39,462
and talk on their own, interesting
processes and productivities can emerge.

225
00:11:39,462 --> 00:11:42,403
And now I think next time
you go to your front step

226
00:11:42,403 --> 00:11:44,914
and pick up that box that
you just ordered online,

227
00:11:44,914 --> 00:11:47,138
you break it open and
the goo is in there,

228
00:11:47,138 --> 00:11:49,891
you'll have some wonderment
as to whether a robot

229
00:11:49,891 --> 00:11:52,484
assisted in the picking
and packing of that order.

230
00:11:52,484 --> 00:11:54,163
Thank you

231
00:11:54,163 --> 00:11:58,793
(Applause)