シャドーイング練習: Inside a warehouse run by AI robots - YouTubeで英語スピーキングを学ぶ
C1
We're enabling the next generation of Amazon to really grow
149 文
文が短すぎたり長すぎる場合は、Editをタップして調整してください。
1
We're enabling the next generation of Amazon to really grow
2
and realize their full potential and driving the economy forward because this is the future of logistics.
3
I'm Andre, Chief Growth Officer at BrightPick,
4
and we're developing the next generation of warehouse robotics.
5
Our mission is really to enable any warehouse,
6
large or small, to fully automate their order fulfillment in a matter of weeks.
7
So right now we're standing in one of our installations
8
where we pretty much automated the entire fulfillment process using close to 50 BrightPick Autopicker robots.
9
I'm going to show you around so you can see how it looks.
10
So our flagship robot is called BrightPick Autopicker
11
and it's actually the only mobile robot in the world that not only transports items but can also robotically pick them.
12
And the big advantage with that is it actually does the pick directly in and out.
13
And we actually took a lot of inspiration from the way humans do picking because humans,
14
they go directly from one pick to the next and that is actually the most efficient way to pick orders.
15
Basically, what we did is you can think of BrightPick Autopicker
16
as almost like a human with a cart moving from one location in the warehouse to the next
17
and doing the picks as it goes on.
18
In fact, we're getting pretty close to human level performance and at a fraction of the cost.
19
So the way the robotic picking process works is the robots,
20
they retrieve a storage tote from the shelving,
21
they scan the storage tote,
22
create a 3D model of the tote.
23
Then we have an AI engine which tells the robot what item to pick based on probability of success,
24
and then the robot picks that item from the storage toad into the order toad.
25
The thing with robotic picking is that inevitably the robots will not be able to pick some items some of the time.
26
I think anyone who tells you they can pick all items 100% of the time are lying, frankly.
27
It's a big challenge in robotic picking in terms of what do you do as a fallback in that scenario.
28
We're actually not entirely relying on robotic picking here.
29
We incorporated a couple of goods-to-person stations into this installation,
30
both as a fallback in case the robots can't pick the items,
31
but also for items that aren't ideally suited for robotic picking.
32
So let's say items that are heavier or that have a changing center of gravity,
33
like liquids, for example.
34
So this is our goods to person station right here.
35
It actually works on the same principle as the robotic picking.
36
So each auto picker brings both the storage tote and the order tote to a human operator.
37
There's a tablet that tells him exactly how many items and
38
which items he needs to pick and then the operator picks it from one tote to the other tote.
39
So it's super simple, pretty ergonomic.
40
The robots they raise both totes to waist height.
41
They actually have four different sides.
42
So what that enables us to do is to feed the human operator from four sides at the same time.
43
So during peak hours when it's really busy,
44
there's basically four robots at the station at any given point in time,
45
which means there's like zero idle time in between fixed.
46
A really important part of our philosophy is product simplicity and cost.
47
You can see like we use a pretty simple SCAR arm on the robots.
48
It's two axes, the end effector is pretty flexible
49
and we could have of horse stuck like an expensive six-axis arm on the robot,
50
but that would have basically doubled the cost for an extra 10% of performance.
51
There's no point in doing that
52
when basically what we do in those 10% of the edge cases is we take those items to a human operator,
53
which you would anyways need because even if you have the most expensive robotic picker in the world,
54
there's still going to be some items when the robot can't pick them.
55
So you anyways have to solve for that.
56
And I think that's I think that's a really important part to understand about the whole BrightBix system is
57
it's designed with simplicity in mind.
58
So there's a lot of super complicated features,
59
AI, you know, the software orchestration behind it.
60
But the actual process of working with the robots and installing it in the warehouse,
61
it's super simple, right?
62
You see I'm like walking around with the robots.
63
Of course, usually we all want people to do that because it slows down the system.
64
But it's perfectly safe, you know,
65
you don't need any safety fencing.
66
There's no QR codes on the floor for navigation.
67
We use LiDARs and AI.
68
The shelving, it's like very cheap.
69
It's basically the same shelving you can buy in Home Depot,
70
which also means like you can install in a matter of weeks and even move the shelving from one warehouse to another,
71
which, you know, it's pretty important.
72
You don't want to build like a monument in your warehouse that you're stuck with for the next 10 years.
73
That's actually the reason we purposefully don't use any conveyors because,
74
you know, once you build a conveyor good luck moving that.
75
That's basically why we developed the system is to enable any retailer to automate their fulfillment in a matter of weeks.
76
This is really like a decade of development behind this.
77
I mean first we developed the 3D scanner which is actually from our sister company Photo Neo.
78
We then developed the AI picking engine.
79
I think we've done close to a billion picks by now to train our AI.
80
We then developed a mobile platform,
81
all the software orchestration that goes with that.
82
We actually had a goods-to-person solution before this,
83
but then ultimately we brought it all together inside the Autopicker.
84
And now this robot can do everything you need for order fulfilling, right?
85
Like robotic picking, goods-to-person picking,
86
pallet picking, order buffering, consolidation, dispatch, replenishment.
87
When we think of BrightPick Autopicker as basically a humanoid in all but name,
88
If you think about what a human picker does in a warehouse,
89
it's basically the same, except auto pickers are able to do it much faster, more efficient.
90
It's literally a tenth of the cost of a humanoid.
91
We don't believe in technology for technology's sake.
92
Why do you need a human form factor when you can basically achieve human level performance at a fraction of the cost?
93
So a common misconception that people have about robotics is that we're taking away people's jobs,
94
but the reality is actually completely opposite because pretty much every customer that buys our solution,
95
they're dealing with massive labor shortages,
96
whether it's in logistics or in manufacturing,
97
and there's simply not enough people to meet demand because we have a shrinking labor force.
98
These are physically tough jobs.
99
Imagine walking two marathons a week just to pick orders,
100
and there's not enough people to fill the demand, basically.
101
For example, this customer right here,
102
they had to actively turn off their marketing spend because they didn't have enough people in their warehouse to pick orders.
103
And now after they installed our solution,
104
they're able to grow it 100%.
105
It was basically like three people servicing our entire system.
106
Whereas before they would have needed 20, 30 people here.
107
Another feature that's unique to BrightPick is what we call pallet picking.
108
And this is actually, imagine you have items that are fast movers.
109
So let's say you're putting in samples or you're basically selling products that go into every order or every second order.
110
It doesn't really make sense to put those items into the system
111
because you're going to be replenishing them almost as fast as you're taking them out.
112
So what we developed, what we call these pallet picking positions,
113
where basically human operators are able to pick directly from pallets or from cases,
114
which you see stored behind them,
115
and place them onto the order tote at the robot.
116
So that basically makes the replenishment process super easy,
117
where all you do is you stick a pallet there or you throw a case there,
118
and then the robot pulls up,
119
tells the human operator on the tablet what item to pick,
120
and the human can pick that item and place it onto the robot.
121
So you really get that flexibility of robotic picking,
122
GTP picking, and pallet picking,
123
all as part of one system.
124
You really don't need any other picking.
125
So this right here is the buffer area,
126
and actually this is a 24-7 operation,
127
so the robots are working even at night when there's practically no one in the warehouse.
128
and what they're doing is after they pick the orders,
129
they buffer them in this area.
130
And then once the morning shift comes in,
131
they take them out, deliver them to pack out to be packed and shipped.
132
Another use case is imagine you have an order that consists of 10 picks,
133
but only nine of them are robotically pickable.
134
So the robots are gonna pick those nine items overnight,
135
buffer them, and then when the morning shift comes in,
136
it's gonna do that last 10th pick using the goods to person or pallet station.
137
And basically then the order is complete.
138
So because we have such a high level of automation,
139
we're able to easily operate at night because you practically don't need anyone to run the system.
140
We're now in a hyper-growth mode.
141
We're really focused on ramping up our manufacturing because we already get more demand than we can meet for our solution.
142
So now it's really about laying down the groundwork to make
143
sure we can manufacture as many of these robots as possible and really ensure that they're as reliable as possible.
144
We understand that these are mission critical processes,
145
so we make sure that each robot can really operate five,
146
10 years without breaking down.
147
This is one of many installations that we've already done.
148
We have many more in the pipeline,
149
so right now it's rolling up our sleeves and getting to work.
アプリをダウンロード
話したすべての文をAIが採点
TRENDING
人気動画
このレッスンについて
このレッスンでは、最新のAIロボット技術を利用した倉庫自動化について学びます。ビデオでは、BrightPick Autopickerというロボットがどのようにして効率的に商品を選び、倉庫内で注文を履行するのかを解説しています。この内容を通じて、英語のスピーキング技術を磨き、特に現代の物流業界における専門用語を習得することが目指せます。
重要な語彙とフレーズ
- 自動化 (Automation) - 作業を自動的に行うプロセス。
- 倉庫 (Warehouse) - 商品を保管するための場所。
- ロボティックピッキング (Robotic Picking) - ロボットによる商品の選択。
- AIエンジン (AI Engine) - 人工知能を利用した解析システム。
- オーダー (Order) - 注文。
- 人間オペレーター (Human Operator) - 商品を手動で選ぶ人。
- 確率 (Probability) - 物事が起こる可能性。
- アクセシビリティ (Accessibility) - 人にとっての利用しやすさ。
練習のコツ
このビデオのスピードとトーンに合わせてシャドーイングを行う際には、以下のポイントに注意しましょう。まず、ナレーターの言葉をよく聞き、リズムやイントネーションを真似てみてください。特に「商品を選ぶ」「倉庫を自動化する」などの専門用語を口に出して練習することで、英語スピーキング練習において具体的な表現力を高めることができます。
また、shadow speakのテクニックを用いて、ビデオの音声と同時に声に出すことで、リアルタイムでのスピーキング力を向上させましょう。YouTubeで英語学習を楽しみながら、自分の発音や流暢さが向上していくのを感じられるはずです。この練習法は、特にIELTS スピーキング対策にも役立ちますので、ぜひ取り入れてみてください。
シャドーイングとは？英語上達に効果的な理由
シャドーイング（Shadowing）は、もともとプロの通訳者養成プログラムで開発された言語学習法で、多言語習得者として知られるDr. Alexander Arguelles によって広く普及されました。方法はシンプルですが非常に効果的：ネイティブスピーカーの英語を聞きながら、1〜2秒の遅延で声に出してすぐに繰り返す——まるで「影（shadow）」のように話者を追いかけます。文法ドリルや受動的なリスニングと異なり、シャドーイングは脳と口の筋肉が同時にリアルタイムで英語を処理・再現することを強制します。研究により、発音精度、抑揚、リズム、連音、リスニング力、そして会話の流暢さが大幅に向上することが確認されています。IELTSスピーキング対策や自然な英語コミュニケーションを目指す方に特におすすめです。