English subtitles

← What happens inside those massive warehouses?

We make millions of online purchases daily, but who (or what) actually puts our items into packages? In this talk, Mick Mountz weaves a fascinating, surprisingly robot-filled tale of what happens inside a warehouse.

Get Embed Code
25 Languages

Showing Revision 8 created 09/24/2014 by Morton Bast.

  1. I want to talk to you about,
  2. or share with you, a
    breakthrough new approach
  3. for managing items of
    inventory inside of a warehouse.
  4. We're talking about a pick,
    pack and ship setting here.
  5. So as a hint,

  6. this solution involves
    hundreds of mobile robots,
  7. sometimes thousands
    of mobile robots,
  8. moving around a warehouse.
    And I'll get to the solution.
  9. But for a moment, just think
  10. about the last time that
    you ordered something online.
  11. You were sitting
    on your couch
  12. and you decided that you
    absolutely had to have this red t-shirt.
  13. So — click! — you put it
    into your shopping cart.
  14. And then you decided
    that green pair of pants
  15. looks pretty good too — click!
  16. And maybe a blue
    pair of shoes — click!
  17. So at this point you've
    assembled your order.
  18. You didn't stop to think
    for a moment that
  19. that might not be a great outfit.
  20. But you hit
    "submit order."
  21. And two days later, this package
    shows up on your doorstep.
  22. And you open the box and you're
    like, wow, there's my goo.
  23. Did you ever stop to think about
    how those items of inventory

  24. actually found their way inside
    that box in the warehouse?
  25. So I'm here to tell you
    it's that guy right there.
  26. So deep in the
    middle of that picture,
  27. you see a classic
    pick-pack worker
  28. in a distribution or
    order fulfillments setting.
  29. Classically these pick workers will
    spend 60 or 70 percent of their day
  30. wandering around
    the warehouse.
  31. They'll often walk
    as much as 5 or 10 miles
  32. in pursuit of
    those items of inventory.
  33. Not only is this an
    unproductive way to fill orders,
  34. it also turns out to be an
    unfulfilling way to fill orders.
  35. So let me tell you where I
    first bumped into this problem.

  36. I was out in the Bay area
    in '99, 2000, the dot com boom.
  37. I worked for a fabulously
    spectacular flame-out called Webvan.
  38. (Laughter)
  39. This company raised hundreds of
    millions of dollars with the notion that
  40. we will deliver
    grocery orders online.
  41. And it really came down to the fact
    that we couldn't do it cost effectively.
  42. Turns out e-commerce was something
    that was very hard and very costly.
  43. In this particular instance we were trying
    to assemble 30 items of inventory
  44. into a few totes, onto a van
    to deliver to the home.
  45. And when you think about it,
    it was costing us 30 dollars.
  46. Imagine, we had an
    89¢ can of soup
  47. that was costing us one dollar to
    pick and pack into that tote.
  48. And that's before we actually
    tried to deliver it to the home.
  49. So long story short,
    during my one year at Webvan,

  50. what I realized by talking to
    all the material-handling providers
  51. was that there was no solution designed
    specifically to solve each base picking.
  52. Red item, green, blue, getting
    those three things in a box.
  53. So we said, there's just
    got to be a better way to do this.
  54. Existing material handling
    was set up to pump
  55. pallets and cases of
    goo to retail stores.
  56. Of course Webvan went out of business,
    and about a year and a half later,

  57. I was still noodling on this problem.
    It was still nagging at me.
  58. And I started
    thinking about it again.
  59. And I said, let me just focus briefly
    on what I wanted as a pick worker,
  60. or my vision for
    how it should work.
  61. (Laughter)
  62. I said, let's focus
    on the problem.
  63. I have an order here and what
    I want to do is I want to put
  64. red, green and blue
    in this box right here.
  65. What I need is a system where I put out
    my hand and — poof! —
  66. the product shows up
    and I pack it into the order,
  67. and now we're thinking,
  68. this would be a very operator-centric
    approach to solving the problem.
  69. This is what I need. What technology
    is available to solve this problem?
  70. But as you can see, orders can come
    and go, products can come and go.
  71. It allows us to focus on making the
    pick worker the center of the problem,
  72. and providing them the tools to make
    them as productive as possible.
  73. So how did I
    arrive at this notion?

  74. Well, actually it came from
    a brainstorming exercise,
  75. probably a technique
    that many of you use,
  76. It's this notion of
    testing your ideas.
  77. Take a blank sheet, of course,
  78. but then test your ideas
    at the limits — infinity, zero.
  79. In this particular case, we
    challenged ourselves with the idea:
  80. What if we had to build a
    distribution center in China,
  81. where it's a very,
    very low-cost market?
  82. And say, labor is cheap,
    land is cheap.
  83. And we said specifically,
  84. "What if it was zero dollars
    an hour for direct labor
  85. and we could build a million-
    square-foot distribution center?"
  86. So naturally that
    led to ideas that said,
  87. "Let's put lots of people
    in the warehouse."
  88. And I said, "Hold on,
    zero dollars per hour,
  89. what I would do is 'hire'
  90. 10,000 workers to come to the
    warehouse every morning at 8 a.m.,
  91. walk into the warehouse and
    pick up one item of inventory
  92. and then just stand there.
  93. So you hold Captain Crunch,
    you hold the Mountain Dew,
  94. you hold the Diet Coke.
  95. If I need it, I'll call you,
    otherwise just stand there.
  96. But when I need Diet Coke and I call it,
    you guys talk amongst yourselves.
  97. Diet Coke walks up to the front —
    pick it, put it in the tote, away it goes."
  98. Wow, what if the products
    could walk and talk on their own?
  99. That's a very interesting,
    very powerful way
  100. that we could potentially
    organize this warehouse.
  101. So of course,
    labor isn't free,

  102. on that practical
    versus awesome spectrum.
  103. (Laughter)
  104. So we said mobile shelving —
    We'll put them on mobile shelving.
  105. We'll use mobile robots and
    we'll move the inventory around.
  106. And so we got underway on that and
    then I'm sitting on my couch in 2008.
  107. Did any of you see the Beijing
    Olympics, the opening ceremonies?
  108. I about fell out of my
    couch when I saw this.
  109. I'm like, that was the idea!
  110. (Laughter and Applause)
  111. We'll put thousands of people on
    the warehouse floor, the stadium floor.
  112. But interestingly enough, this
    actually relates to the idea
  113. in that these guys were creating some
    incredibly powerful, impressive digital art,
  114. all without computers,
    I'm told,
  115. it was all peer-to-peer
    coordination and communication.
  116. You stand up,
    I'll squat down.
  117. And they made
    some fabulous art.
  118. It speaks to the
    power of emergence
  119. in systems when you let things
    start to talk with each other.
  120. So that was a little
    bit of the journey.
  121. So of course, now what became
    the practical reality of this idea?

  122. Here is a warehouse.
  123. It's a pick, pack and ship center
    that has about 10,000 different SKUs.
  124. We'll call them red pens,
    green pens, yellow Post-It Notes.
  125. We send the little orange robots
    out to pick up the blue shelving pods.
  126. And we deliver them
    to the side of the building.
  127. So all the pick workers now
    get to stay on the perimeter.
  128. And the game here is
    to pick up the shelves,
  129. take them down the highway and
    deliver them straight to the pick worker.
  130. This pick worker's life
    is completely different.
  131. Rather than wandering around
    the warehouse, she gets to stay still
  132. in a pick station like this
  133. and every product in the
    building can now come to her.
  134. So the process
    is very productive.

  135. Reach in, pick an item,
    scan the bar code, pack it out.
  136. By the time
    you turn around,
  137. there's another product there
    ready to be picked and packed.
  138. So what we've done is take
    out all of the non-value added
  139. walking, searching,
    wasting, waited time,
  140. and we've developed a very
    high-fidelity way to pick these orders,
  141. where you point at it with
    a laser, scan the UPC barcode,
  142. and then indicate with a light
    which box it needs to go into.
  143. So more productive, more
    accurate and, it turns out,
  144. it's a more interesting office
    environment for these pick workers.
  145. They actually complete
    the whole order.
  146. So they do red, green and blue,
    not just a part of the order.
  147. And they feel a little bit more
    in control of their environment.
  148. So the side effects
    of this approach

  149. are what really surprised us.
  150. We knew it was going
    to be more productive.
  151. But we didn't realize just how
    pervasive this way of thinking
  152. extended to other
    functions in the warehouse.
  153. But what effectively this approach
    is doing inside of the DC
  154. is turning it into a massively
    parallel processing engine.
  155. So this is again a
    cross-fertilization of ideas.
  156. Here's a warehouse
    and we're thinking about
  157. parallel processing
    supercomputer architectures.
  158. The notion here is that you have
  159. 10 workers on
    the right side of the screen
  160. that are now all independent
    autonomous pick workers.
  161. If the worker in station three decides
    to leave and go to the bathroom,
  162. it has no impact on the
    productivity of the other nine workers.
  163. Contrast that, for a moment, with the
    traditional method of using a conveyor.
  164. When one person
    passes the order to you,
  165. you put something in
    and pass it downstream.
  166. Everyone has to be in place
    for that serial process to work.
  167. This becomes a more robust
    way to think about the warehouse.
  168. And then underneath the hoods gets
    interesting in that we're tracking

  169. the popularity
    of the products.
  170. And we're using dynamic
    and adaptive algorithms
  171. to tune the floor
    of the warehouse.
  172. So what you see here potentially
    the week leading up to Valentine's Day.
  173. All that pink chalky candy has
    moved to the front of the building
  174. and is now being picked into a
    lot of orders in those pick stations.
  175. Come in two days after Valentine's Day,
    and that candy, the leftover candy,
  176. has all drifted to the
    back of the warehouse
  177. and is occupying the cooler
    zone on the thermal map there.
  178. One other side effect of this
    approach using the parallel processing
  179. is these things can
    scale to ginormous.
  180. (Laughter)
  181. So whether you're doing
    two pick stations, 20 pick stations,
  182. or 200 pick stations, the
    path planning algorithms
  183. and all of the inventory
    algorithms just work.
  184. In this example you
    see that the inventory
  185. has now occupied all the
    perimeter of the building
  186. because that's where
    the pick stations were.
  187. They sorted it
    out for themselves.
  188. So I'll conclude with
    just one final video

  189. that shows how
    this comes to bear
  190. on the pick worker's actual
    day in the life of.
  191. So as we mentioned, the process is
    to move inventory along the highway
  192. and then find your way
    into these pick stations.
  193. And our software in the background
  194. understands what's going on
    in each station,
  195. we direct the pods
    across the highway
  196. and we're attempting to
    get into a queuing system
  197. to present the work
    to the pick worker.
  198. What's interesting is we can even
    adapt the speed of the pick workers.
  199. The faster pickers get more pods
    and the slower pickers get few.
  200. But this pick worker now is
    literally having that experience
  201. that we described before.
  202. She puts out her hand.
    The product jumps into it.
  203. Or she has to reach in and get it.
  204. She scans it and
    she puts it in the bucket.
  205. And all of the rest of the technology
    is kind of behind the scenes.
  206. So she gets to now focus on the
    picking and packing portion of her job.
  207. Never has any idle time,
    never has to leave her mat.
  208. And actually we think
    not only a more productive
  209. and more accurate
    way to fill orders.
  210. We think it's a more
    fulfilling way to fill orders.
  211. The reason we can say
    that, though, is that workers

  212. in a lot of these
    buildings now compete
  213. for the privilege of working
    in the Kiva zone that day.
  214. And sometimes we'll catch
    them on testimonial videos
  215. saying such things as,
  216. they have more energy after the
    day to play with their grandchildren,
  217. or in one case a guy said, "the
    Kiva zone is so stress-free
  218. that I've actually stopped taking
    my blood pressure medication."
  219. (Laughter)
  220. That was at a pharmaceutical distributor,
    so they told us not to use that video.
  221. (Laughter)
  222. So what I wanted to leave you
    with today is the notion that

  223. when you let things start
    to think and walk
  224. and talk on their own, interesting
    processes and productivities can emerge.
  225. And now I think next time
    you go to your front step
  226. and pick up that box that
    you just ordered online,
  227. you break it open and
    the goo is in there,
  228. you'll have some wonderment
    as to whether a robot
  229. assisted in the picking
    and packing of that order.
  230. Thank you.

  231. (Applause)