Too Soon?...Too Late?...Too Wrong?...or To Be?: Perspectives on adidas' Speedfactory (& Nike Flex) collaboration closures

Back in July 2019 I had the opportunity to drive a Tesla Model S P100D down the Pacific Coast Highway in California and some choice roads off it - and when I say drive, I don't mean the typical plodding around the town doing a Driving Miss Daisy (look it up, you yung'uns) impersonation. I mean numerous launches using Ludicrous mode, corners taken at speeds that had the tyres screaming for mercy / return to sanity and a first degree murder charge for what I did to those poor brakes. But it was an opportunity to really test the limits of a car that more than any other in my lifetime, has rewritten the rules of the future of the automobile.

The Tesla Mdole S P100D: The product of a disruptive company with a radical approach to electrification, this car reset expectations of what a large sedan was capable of - and that performance and environmental friendliness were not mutually exclusive. But bringing this car to market required a lot of industry 4.0 technology...and thinking. How did Nike and adidas fair with their approach? Oh...and it's an amazing drive, though please always drive sensibly, unlike the author...(Image:Tesla)
The acceleration was insane: lineball with a Porsche Turbo S up to about 180 km/h. For a (very) heavy 4 door sedan, that's jaw dropping. Handling was quite remarkable for such a big, porky car, thanks to the low centre of gravity and favourable inertial moment caused by the battery pack layout. Interior design was truly minimalist and effective. It was a revelation: this was the which I would likely play no part in if I kept up this type of driving.

The internal combustion motor may not be dead, but over that weekend I saw many new lines added to its obituary. Whilst the Tesla is far from perfect (fit, finish & assembly quality, the lifeless steering, some weird software quirks and what I can only describe as a slight "out of sync"; the accelerator, brakes and steering all seem to be a fraction of a second ahead or behind each other depending on conditions, making good driving at speed nigh on impossible), it's clear that if a Lithium Ion battery pack and electric motors can achieve this today after a relatively brief development time, then the future is electric.

And it's only taken 120+ years.

If I Could Turn Back Time...

As surprising as it is to many, back in 1900, more than 35% of the vehicles on US roads were electric, and by the early 1910s, the number was exceeding 40%. Yes - America almost had an electric road future before today's Tesla buyer's grandparents were born.

But it was not to be. The limited range of electric cars (less than 70 km in real world situations) and the expanding infrastructure of petrol stations combined with the advent of the low cost Ford Model T to make electric cars less able to meet the people's expectations. Simply, the total eco-system (or super-system) of the Model T, its successors and indeed all internal combustion engine powered cars proved a market success and serious interest in electric cars stalled for almost a century.

But technology and thinking moves on, and sometimes it does so with ideas from the past that suddenly become fashionable and viable. Electric cars were limited by the primitive lead-acid battery technology of most of the 20th century and CO2 emissions from cars was a non-issue until the 2000s. But since the turn of the century, lithium ion battery technology has combined with strong environmental awareness to make electric cars more than a curiosity...and as Tesla has shown, one company taking a huge risk with a few advanced technologies can totally transform an industry, or at least get the ball rolling on the change.

The Tesla Factory in Fremont, CA. Even by auto industry standards, where robotics have played a huge role in vehicle assembly since the 1990s, Tesla use of robotics sets new standards in . Sadly, as of the end of 2019, the quality produced by this factory leaves a lot to be desired. Whilst this industry 4.0 technology promises perfection in theory, the real world has proven to have little respect for theory...(Image: Tesla)
So with that in mind...what are we to make of one of the first real world examples of Industry 4.0 being shut down in the Mexico, the US and Germany this over the past 2 years with Nike and adidas closing some cutting edge facilities?

Huh? What do shoes have to do with Teslas? As it turns out, quite a lot. Tesla represents new thinking in both product and the production processes to realise it. It is a company that more than any other has disrupted the established players, and its use of robotics is at another level compared to existing car companies. And in that sense, it has sought to achieve over the past decade what both Nike and adidas have tried to go for over the past 3 years. The end results, however, are now likely to be very different.

The World of Sneakers...and Sneakers for the World

The athletic shoe industry has - arguably - epitomised globalisation more than any other. With 90%+ of production of athletic footwear from the major brands being sourced from Asia to be sold the world over for over 3 decades, the likes of adidas Nike, Puma, New Balance et al have built corporate empires based on an enviable blend of fashion, fitness and performance - as well as low cost manufacturing. These elements combine to create desirable, high turnover and high margin products - and ones which have the distinction of being a fashion item that men of all age brackets can appreciate, something that can't be said of almost any other piece of apparel, where women's fashion awareness far outstrips that of most guys.

But the challenges in this industry using this model are many - one of the major ones being long lead times (I'll save the protectionist resurgence for another time). From design concept to being on retail shelves in Europe and North America, a new sneaker design can take upwards of 18 months in a worst case scenario - and worst cases are all too common. 12 months can be achieved in some situations, with shorter times possible if a company is modifying an existing model. But this is an industry that constantly demands fresh new ideas to satisfy a market that is fickle yet set in its ways. There are only a handful of iconic models from major brands being able to be produced year in, year out as staples (such as the Nike Air Force 1, the adidas Superstar and the New Balance 574). All too often, new designs fail in the market due to the inability to respond to new trends (and the inability to create new ones), delays in getting the right product to the right location, supply/demand misalignment and failures in product design/quality.

The above occurs in part due to supply chain complexity: long lead times are often the price paid for of low cost component sourcing, with dozens of suppliers of such items of knits uppers, rubber outsoles, shoe laces and midsoles having to tightly coordinate movements of components to enable lean manufacturing. Having worked in this sector recently, I have seen amazing efforts by skilled managers to make these complex systems work in the real world - think of juggling a bunch of chainsaws, electric knives and hand grenades whilst wearing a pair of dark sunglasses and tap dancing through a minefield with a hungry Bengal tiger circling about - that's what it often feels like for , especially in the age of The Orange Tariff Man.

If only there was a way to quickly respond to consumer needs close to their location, to offer a high degree of cost effective customization, to have a lead time measured in days rather than months and to simply - give something better for every stakeholder.

Enter Industry 4.0.

Whilst more a subset of the Fourth Industrial Revolution than a different way of saying the same thing - and of course exact definitions that everyone agrees upon are not to be found - it is generally characterised by a number of attributes which include:
  1. Usage of large data sets from various sources to uncover hidden trends / desires / potential
  2. Robotics performing more and more tasks formerly done by people
  3. Internet of Things enabling more automated / intricate / accurate / timely production processes
  4. Artificial Intelligence technologies to assist in decision making at multiple levels / stages
  5. 3D printing and advanced additive and related manufacturing technologies
  6. Agility with machine / human process configuration
  7. Advanced simulation "what if" scenario modelling
  8. Augmented reality to assist humans with new perspectives
  9. Cloud technology
When configured correctly, the above is destined / expected / hoped to eventually enable any individual to go into a footwear store (or a podiatrist clinic, or even from home), have their feet/stride scanned and within a day or a few hours, be able to pickup a bespoke, 'perfect' pair of shoes that optimally meets the customers' needs /desires in a way no shoe currently can. The customer can spec the shoe exactly how they want (sizing, style, colors, materials, shaping etc), or can let the AI technology decide what is best for them. A shoe will be 'printed'/assembled for them on the spot or close by and be on their feet in as little as a few hours. If desired, the shoe is embedded with technologies that enable real time monitoring of wearer performance/health, for further improvements on new shoes and perhaps modifications on the existing one.

Broadly, the above is the goal of both Nike and adidas, as well as many other companies. But it's really only been both those companies that have put in the commitment - and dollars - to really push hard with Industry 4.0. 

Two Titans

In October 2015, Nike announced a partnership with Flex (formerly Flextronics), to help create a new type of manufacturing and supply chain model that will take advantage of Industry 4.0 thinking and deliver new ways of designing, making and selling footwear, with a new facility in Guadalajara, Mexico. This would produce shoes for Nike athletes and act as a template for the next generation factory/store concept.

Not be outdone, in the same month adidas soon announced its own initiative, which would see a new facility launched in Ansbach, called the Speedfactory. It later announced that a sister facility would be built in Atlanta, Georgia.

adidas partnered with a myriad of expert firms firms to help bring the 4.0 vision to life. This included Johnson Controls (systems integration), Manz (engineering consultants) and KSL Kleimann (robotic assembly/configuration specialists).

So far, so good: two of the biggest industry players leading the charge into the future with highly skilled partners, with a clear vision of what they wanted and a determination to rewrite the rulebook as to how shoes are designed, made and sold.

Let's have a brief look at some parts of the Speedfactory and its products...

adidas AM4LDN
The adidas AM4LDN sneaker is a prime example of Industry 4.0 and Lean thinking combined: absolute minimalism in product enabled by advanced design and manufacturing technology. But the entire platform that created this shoe may be both a little ahead of its time...and in other ways not really much of an advance over current best practices. (Image: adidas)

The Speedfactory in Atlanta is roughly the size of a smaller big box store, about 7,000m2. And from the moment you walk in, you get the impression you are where everyone else will be in 10-20 years. The machinery is somehow familiar yet radically different once you examine them, the layouts initially look crazy but soon make some sense. And then you start to think about the parts relating to the whole and the totality of what you perceive.

Whilst for obvious reasons I cannot go into too many details about some of what I witnessed, I did see a very lean manufacturing process that created a very lean sneaker: minimalism was a theme I saw, felt and heard in depth. And to say I was impressed was an understatement. It showed technologies, layouts and processes that represent a radical departure from current well as a few "The more things change, the more they stay the same" moments.

The well known Primeknit upper was being laser cut in a way that was largely familiar to me (the earlier process of its creation was more impressive) but with some clear improvements. These two stages were the first of my "Wow!" moments. Next was the shaping and sewing stage. 

This was my first "Oh" moment. 

It was very familiar. I have seen it replicated many times before, including in one of the most non automated factories I have ever seen. And that really brought something home to me.

Industry 4.0 is not about automation as much as it is humans and technologies working together in new well as old ones. The simply reality for now and the near future is that working with soft, pliable materials to shape them and sew them is something that no technology can yet match the capability of a well trained pair of eyes, an optic nerve or two, a skilled pair of fingers and a brain in reasonably good condition.

What a strange looking robot... A very human worker in the Ansbach Speedfactory performs the final stitching steps of the knit upper of the AM4LDN, prior to the breakthrough process of heat fuse-bonding to the midsole. The difficulty in working with soft, highly flexible materials highlights the limits of current machine technology and shows that Industry 4.0 will be a combination of automation and machine/human collaboration.
But then things took a turn for the better again. Arguably, the most interesting process adidas has (mostly) perfected with is the fuse bonding method. Normally, the midsole is glued and stitched to the upper, a process which is cumbersome and must be done by hand. It often results in glue stains and less than perfectly aligned uppers/midsoles.

Fuse bonding is different. It technically means no adhesive is used (in practice this is not always the case, depending on materials; often, a thin adhesive layer is added between the materials at some stage or there is an adhesive built into either or both of the materials, providing additional bonding strength/longevity.) as the joining process is made permanent by a chemical/ionic bond between the two materials.

Here, I saw the knit uppers being reshaped by specially designed and operated machines, attached to the midsoles by pressers, then put into a special oven like device and after being subject to a series of processes that radiated heat, were fused together to form the shoe in an intricate ballet between human and machine, in a manner very different to a manual process.

With the upper over the last, the mating to the midsole is about to happen. Note this automated process relies on a camera. The reliability and accuracy of this setup has been improved with usage of a series of lasers, a technology which a number of contract manufacturers are keen to get their hands on.
Of course, threading the laces was then done by a human - it will be a sorry day for humanity when a robot is able to perform that task.

The above is a very simplified view, but that fuse bonding process is a true breakthrough: glue in shoes is often a weakspot in terms of heat resistance and long term durability, one that now seems to have been solved.

All in all, this was most impressive. After the above and many many observations and discussions, I walked away thinking this was the future, pure and simple.

But all went wrong. And fast.

The Wheels Come Off

Already by late 2018, Nike killed off its deal with Flex, and in early November 2019, adidas confirmed it was shutting down its Speedfactory sites in both Ansbach, Germany and Atlanta, USA. But more than that, some of the technologies and processes would be shared with existing contract manufacturers in Asia.

An entire system that many feared was set up to replace the Asian manufacturing juggernauts will now assist them.

The adidas timing was interesting from my perspective: it happened about 12 hours after I had finished visiting the Atlanta site. During my tour, only about 3 people at the site were aware of what was about to happen, though rumours had been flying around for the past few months.

This is not the way Industry 4.0 was supposed to go.

Whether fast or slow, the integration of IoT, 3D printing, various and a bevy of more specialized manufacturing technologies was supposed to be inevitable and irreversible. And with both adidas and Nike keen to reduce the huge lead times for highly seasonal/trend sensitive footwear, you'd think that their Industry 4.0 factories located within a few kilometres of major population centres - and in some cases right within them - would be a no-brainer.

So what happened?

The reasons vary, depending on who you believe - and my discussions with key players have left me with the impression of a 'work in progress' for an answer. The simple headline of "It costs too much to do it this way" is not incorrect, but it is but one ingredient of a complex recipe. 

With Nike, the issue seems to be simply the inability to work out a commercially viable arrangement that Flex would accept - and after speaking to a number of contract shoe manufacturers recently, it is pretty clear Nike is always borderline sadistic in price negotiations with its suppliers in every part of the value chain. They know their market power and use it mercilessly. Flex simply could not abide by Nike's terms so best to call it a day.

And what of adidas? Why did they not want to play this game?

Great Expectations?

The adidas Speedfactory was not so much factory as a laboratory: one of the most advanced examples of what re-shored, mass customized manufacturing would look like - or so we all thought. And even though a number of adidas executives said that it would never replace the outsourced manufacturing model, it seems that other adidas executives always had a plan that it would - and that was the only reason they saw to pursue it. Even now, there is a lot of soul searching in adidas as to the next steps. But it is worth understanding a bit more about the reality of the Speedfactory, or what you see when you peek beyond the marketing hype curtain.

I was advised that the machinery and the layout of the Atlanta site has been in a near state of constant evolution since the day it opened. Simply, there is no template to follow of accepted best practices with this technology: what the machines should be, what they do, how they do it, their configuration/layout, the process steps, what components still had to be made offsite, the type of automation and how it interfaces with the human element. Everything is being created now - and at significant cost in new technology, maintenance practices, layout, testing, reconfiguration etc.

Also, there is a safety issue in some cases: the high performance midsole for some shoes requires chemicals such as hydrazine in the production process - and that's not exactly a substance you want anywhere near an urban (or really any) area. It is simply not going to be possible to economically fabricate certain components of footwear at the site, result in the need to bring some components in, which adds time and may well limit customisation or increase wastage, negating many of this methods advantages.

Next, remember that the current model of "make in Asia and ship to the world" has had over a half a century of operations / supply chain management expertise to be fine tuned: very capable individuals have made a career out of studying ways to improve the transformation of materials into new objects, and getting them to where they need to be. Industry 4.0 technologies have in many cases less than a 5th of that time allocated.

And related to that, I have seen evidence of a view in both companies that perhaps at this early stage, their involvement in designing the ideal processes, procedures and structures to integrate the various technologies was proving a real financial drain, with the light at the end of the tunnel further away than many executives (who live and die by the quarterly reports) wanted. Industry 4.0 is the future, but today is sweating the next quarterly report, with special focus on ..

It seems to come down to expectations: adidas wanted a template for the future that was going to be ready soon for mass rollout. What they got was a laboratory that produced many technical innovations, but that detailed financial analysis showed would almost certainly never be viable without either great breakthroughs in technologies/configurations/operations management knowledge...or a willingness by a substantial portion of the market to pay a significant price premium for the "perfect" sneaker/running shoe. The latter was judged extremely unlikely, the former a total unknown.

And here's the reality.

The Bottom Line Brain

Whilst both Nike and adidas like to innovate, it is only within a certain paradigms: a new foam, a new upper material, a new outsole pattern...this they do. And they do it well.

But Industry 4.0 is way outside those borders that they are comfortable working in. It's a sector that will demand incredible intellectual resources for many years to come - and at a cost that may prove hard to justify to a Board and shareholders.

Despite the slick corporate image of creating /supporting.enhancing elite athletes, the reality of these two companies is not the pie in the sky vision of a startup. It is of established Fortune 500 companies that need to prove their ability to meet KPIs, to ensure that analysts' consensus forecasts are met in the next quarterly report and that the attitude of a relatively small number of analysts to the numbers is positive. They can innovate, but only if they quickly produce results...and that's not the way Industry 4.0 is going to work, at least in the short term.

And this is perhaps why Industry 4.0 is at this stage a bridge too far for the industry: the current executive culture is focused on the near term bottom line, to the exclusion of taking risks outside a set of guidelines. 

And to top it off, there was another issue with adidas: existing supply chain problems. These were alluded to in March 2019, and a bit of investigation reveals problems with responding to positive demand signals, a few bumps in a major ERP rollout and a painful standardisation process with a myriad of Asian suppliers - the final point of which I can more than sympathise with...

These issues are happening now. They are impacting the bottom line. They demand smart people to work hard to solve them. Like many of the smart people currently working in the Speedfactories...

That is the big reason why. adidas had to make a tough call: keep rolling with the Speedfactories that may not see results for a long time, or deploy those resources to resolve critical issues happening now. With one eye on the next quarter's results and the promises made to fix them, the call was pretty obvious. And as stated, it's not a total loss: many of the ideas, technologies and innovations pioneered at the Speedfactory will soon find their may to existing supply chains.

And this is perhaps most realistic: modelling a total value chain for sneakers is an exercise in uncertainty of what the component technologies are...and certainty that mistakes, change and are inevitable. But some elements will be proven fast to work, and with some adaptation, they can be made useful today, rather than waiting for an entire new ecosystem to develop around them.


Ultimately, this is not a good look and not the best of starts for the footwear industries' jump into Industry 4.0...but that is more a reflection of unrealistic time-frame expectations than any fundamental flaw in any of the individual technologies, or the full potential of getting the complete supply chain solution defined. The speedfactory dream of walking into a retail outlet, having your foot/stride scanned and within a timespan of hours having a tailor made, virtually perfect shoe on your feet remains the ultimate prize. But before that goal, there will be many interim prizes: of better fits, faster lead times, superior bio-mechanical performance and greater individual choice - just that it won't all happen at once and in some cases there may need to be a tradeoff with another attribute (most of the time it will be cost).

And there will be stumbles. Plenty. This needs to be accepted as part of the deal to take us to Industry 4.0. It will be messy and painful, indeed fatal for some companies. But that is the price of progress, and it is inevitable.

Meantime, all of us need to keep the faith. Industry 4.0 is the future, though what that term actually means and the supply chains it will spawn are still being defined. But despite this uncertainty, there is one thing we can be sure of:

The tipping point won't take 100 years.

Amazon Robotics Challenge 2017, Nagoya Japan: "Respect CARTMAN'S Authoritah!"

The winning CARTMAN and his Australian Centre for Robotic Vision creators: a low cost, custom made solution that was built to win…and did. But as the basis for a real world mechanical design for an Amazon FC robot picker? Not likely with their current warehouse layout…IMAGE COURTESY OF ACRV.


I have to admit, the win by the Australian Centre for Robotic Vision’s CARTMAN (CARTesian MANipulator) took more than a few observers by surprise…including this writer: the writing was on the wall for a very quick exit from the competition. CARTMAN found his first few days plagued with major malfunctions and a relatively low score during the qualification rounds – hardly the signs of a surefire a winner. But it all came together when it counted and demonstrated that the best approach to the competition was to purpose build a solution to the exact problem from scratch, rather than take an existing apparatus and try to make it do something it was not optimally designed for – the most common approach adopted by other teams. And it also demonstrated it’s possible to do it all on a shoestring budget…with the help of some well-placed cable ties and the very liberal application of duct tape, the engineers best friend.

But there was more to it than that - one of the most important competitions in the world that addresses a perplexing issue of AI - robotic vision. Below, you’ll find a little more about the background to the competition, the current state of robotics and its Artificial Intelligence branches, Amazon’s thinking and what the future holds in the field.


The inaugural Amazon Robotics Challenge (first called the Amazon Picking Challenge) was held in 2015 in Seattle, WA, as part of the International Conference on Robotics and Automation. It was set up to encourage expert teams to develop the technologies that would lead to practical benefits for Amazon Fulfilment Centers (warehouses), as well as act as a talent scouting ground for Amazon Robotics itself. It focuses on resolving one of the most challenging real world tasks for robotics: that of identifying, sorting, picking and stowing various objects in a warehouse.

The competition is now held in sync with Robocup, an international Robotics competition founded in 1997 – which first took the form of a Robotic Soccer match. But since then, the organizers have recognized the need for broader real world appeal (as if soccer didn’t have enough on its own!), and have created various leagues to focus efforts on resolving real world challenges where robotics could have real positive impact. These are broadly classed as:

RobocupSoccer:                The “classic” challenge with a soccer game played between autonomous robots on a 9x6m field.
Robocup@Home:            Robots making lives easier in a domestic setting - a big issue in Japan with its rapidly aging average population (and increasingly in many advanced OECD nations).
RoboCupIndustrial:         Exploring how robots can work in smarter factories, including a logistics competition which focuses on movement of Work In Progress goods between different machines.
RoboCup Rescue:             Emergency Service robots designs going through obstacles that simulate earthquake after effects – again of great practical need to the Japanese.

And of course, the Amazon Robotics Challenge itself, which was carefully watched by a number of players not just in the field, but in the supply chain, retail and investment communities...and the odd consultant.


The word robot comes from the old Slavic word robota, originally implying low level manual labour, in some cases even forced servitude. That has indeed been the reality of the robotics field for many decades: the automation of repetitive, manual type tasks. By contrast, the robotics depicted by the entertainment industry has focused on technologies, capabilities and  - of course – styles far in advance of the reality of the technologies available (from “False Maria” in Metropolis to Bishop in Alien to TARS of Interstellar). However, the reality of Amazon’s business needs has pushed the concept of robotics to new demands.

Robotics itself is a term that covers a vast array of enabling technologies, something perhaps not yet fully appreciated by the supply chain – and broader - community: robotics is an expansive  interdisciplinary collection of disparate fields. They include mechanical engineering, electrical engineering and computer science as well as the dozens of sub-fields that each of these areas encompass.

Depending on the application, a robotics solution still requires various breakthroughs and levels of maturity, which must then be integrated into a workable, commercially viable system. One thing that was clear during the competition is that systems integration remains the key, and is perhaps the greatest challenge of robotics. Individual technical breakthroughs are challenging enough, but getting an entire field of technologies to reach a certain level and then work together is what struck me as something that the very capable teams here – and far beyond - still need time and resources in excess to master.


Amazon’s success in upending traditional retail models is well known, as is the general understanding of its supply chain strengths being a key part of that success. To ensure that edge continues, Amazon’s purchase of Kiva Robotics in 2012 made it a leader in the automated warehouse field, and the soon renamed Amazon Robotics began to play a key role in shaping the future of logistics automation for the company.

Right now, Amazon’s 8th generation Fulfilment Center (warehouse) reflects the leading edge of robotics best practice, with the giant Robo-stow and the Kiva robots giving the company a real edge in efficiency (see here However, the fact that Amazon has been investing massively into Robotics, Artificial Intelligence and Supply Chain over the past few years has led some to conclude that its successful incorporation of all 3 fields has been responsible for its success.

The reality today, however, is a lot more mundane.

In truth, Amazon’s – indeed just about every company’s – utilization of robotics is focused on working around their current limitations as much as exploiting their capabilities. Thus far, robotics is limited to the movement of trays and pallets at the Amazon FC. Using Artificial Intelligence at the warehouse level for picking, sorting and stowing remains a dream just out of reach. 

Whilst Robo-stow is an impressively powerful and dexterous arm, it has about as much true intelligence as an alarm clock. And the Kiva robots that scurry around carrying the sorting trays are little more than “A bunch of Roombas on steroids, except they suck less.”, as was so colourfully put by one anonymous Amazon executive.

The brilliance of the Amazon 8th generation fulfilment centre is its integration of existing technologies with human capabilities, courtesy of outstanding process design. It is a mastery of human and machine systems engineering, rather than Artificial Intelligence, which remains in its infancy in the robotics field.

The Amazon Robotics Challenge is in part designed to help Amazon take the next step in the evolution of the technology ahead of everyone else.


Let’s get this out the way now: CARTMAN is a brilliant way to win a contest and a tribute to the outstanding team behind it, but it has about as much chance of serving as an advanced prototype for a real world picking and stowing robot for an Amazon FC as a home built go-cart has of serving as a base for championship winning F1 car. CARTMAN was designed to a budget for a limited amount of weight and total movement lifespan. It was held together by tape, ties and hope. The concepts of Design for Manufacture/Assembly and Design for Reliability were non-existent in its execution. That said, the gantry crane design intrigued some of the Amazon executives and others: some experimentation is no doubt being mooted at present.

The ARC is a proof of concept competition that allows researchers to demonstrate new thinking and technologies in a competitive - but still very controlled - environment, one where (thus far) budgets have been measured in tens of thousands, rather than tens of millions. But the basic ideas, technologies and thinking can give direction as to where the industry is going. CARTMAN showed that the ideal design for an Amazon FC could be quite different to what most expect...though it may well be the case that the next generation of Amazon FCs could need to have very different configurations to take full advantage of the idea robotic picker design. It will be interesting to follow how Amazon configures its future warehouse designs, if it may adopt a different approach to what we have seen so far with the 8th generation FC.

Look beyond the hardware, of course it’s the software: the robotic vision CARTMAN employed and the algorithms that interpreted the data and made the choices to identify, pick and stow. By the standards of the competition (see below), CARTMAN was fast in identifying objects, though compared to a human picker it was about 25% the speed, at best.

Much work remains to be done.


In observing the teams and their entries over the 3 days, I was in two minds, the result of having two very different frames of reference, given my prior working experience. The part of me that comprehends the technologies associated with robotics (but certainly not to the level of the world class researchers and students who surrounded me) marvelled at how far the experts in the field have come over the past few years in having software and hardware come closer to mimicking the capabilities of people. But the other part of me, the former Lean Six Sigma program manager who had led the creation of countless process maps and time and motion studies of workers at dozens of warehouses around the world lamented at the sheer, mind numbing weakness of the robots compared to their human forebears: the typical Amazon FC worker is able to pick just over 200 items per hour with error rates below 2% (under idealized conditions). The better pickers push that to just over 250 hour with a sub 1% error rate, and the best pickers push that to 300 items per hours sustained, with an error rate that is around 2%.

The robots I saw, by contrast, took an eternity in object recognition, showed real hesitation in movement, painful slowness of articulation and “wing and a prayer” ways of gripping / picking / stowing objects (at times dropping / damaging them). Add to this the fact that transparent objects and certain arrangements of objects presented challenges that pushed the limits of our current understanding of AI, of algorithms and robotic vision to - and often beyond – the limit. 

The really tough challenge I witnessed was the wine glass and the full mineral water bottle: as easily as our human minds can differentiate the two, this remains a stumbling block for robotic vision: transparent objects confound the best software, which became obvious as the robotic arms crashed into the objects, misidentified objects around them and even when they identified an object, they could not pick it up correctly. With a bottle of mineral water, I was advised that even when the object is detected, there is uncertainty as to if it is one whole object, two separate objects separated by the label or if the label portion is the object. Potential fixes include ultrasonic sensors, stereoscopic vision and UV light. But so far, it is early days to get a reliable solution.

Whilst progress has been remarkable over the past few years overall, we have a long way to go – many breakthroughs are still needed across the technological value stream before the fully automated warehouse becomes even remotely feasible for Amazon and its vast product array.


There were 16 teams in total from around the world at the Nagoya International Exhibition Hall. They were mainly University affiliated (graduate and post graduate level), but with some big commercial teams too, such as Applied Robotics and Panasonic. The teams are listed here

The details of what the teams had to contend with can be found at In summary, the rules mean a competitive environment much closer to the reality of an Amazon FC than in the past 2 years…but still, it is far more controlled than what robots would experience if they were dumped into the real world of an Amazon FC. Especially important to note, the teams were allowed to photograph new items 30 minutes before the start of competition. In the real world of an FC, most items passing through would be unknown in terms of size and shape to the same level of detail, or there would be changes in products and packing with no warning in many cases. Those of you in logistics know well the issues in a warehouse: picking, sorting, stowing, packing and moving an ever changing array of near infinitely variable objects in a dynamic environment of varying noise, lighting, obstacles and layout. It’s at times tricky for humans – for robotics, it’s at another level.

This year, Amazon increased the prize money (which perhaps was a bit less than adequate in the past) to USD 250,000 total prize pool with USD 80,000 for the winner. This certainly led to more genuine enthusiasm by all participants - especially some of the less than generously funded University teams...

In quick summary:

Day 1 was for practice rounds only…and just as well, as almost half the teams failed to score any points: machines simply did not work, acted strangely, dropped objects…you name it. But there were two bright spots: a very strong initial performance by the NimbRo team from the University of Bonn and the University of Nanyang from Singapore: the latter had some very impressive algorithms  to identify objects correctly amidst “clutter” (a background / foreground that made the objects challenging to identify), something that drew a lot of attention from the Amazon executives and other teams.

Day 2 was the Stow run: The joint MIT-Princeton team won the day with a solid performance that featured minimal mistakes, though slow speed. Nanyang University again demonstrated great promise with the days runner up award. The ACRV team scored 55 points, despite a fun technical mishap when CARTMAN went a little off the farm and decided to fire the first shots in The Robot Apocalypse by partially self-destructing. A lot of hard work, sweat and tape got him back up.

Day 3 was the Picking run. ACRV got their act together and score 150…but Nanyang stunned with 257, closely followed by NimbRo with 245, both way ahead of everyone else. Speed had shown some improvement, though there were a few drops that again highlighted just how challenging it is to beat the human eye, mind and hand. Most of the teams performed better but there were technical gremlins of various severity and form plaguing just about everyone, showing that this is indeed technology that is largely in the advanced Alpha build stage…

Day 4 was the Final round, where 8 teams had qualified. Simply, it all came together the best for ACRV: CARTMAN behaved (never underestimate the utility of duct tape, Red Bull and sleepless nights for Gen Ys) and showed just how well the team had developed their Robotic Vision solution. Nanyang and NimbRo were the runners up, performing well but just had a few too many drops and errors to win. But the potential of their solutions has been noted by all.


It was a privilege to meet and talk with many of the teams, the commentary on which I could write far more than most are willing to read. Some key observations:

  • Most of the teams bought standard industrial robot arms and relied on a combination software and optimized cameras (which was what ACRV did last year) to give them an advantage. Workable indeed…but not optimal for the contest. It is looking likely next year there will be a lot more customization of the solution done, assuming the conditions are similar to this year. All the teams I spoke to were keen to re-examine the mechanical movement side of the equation, given CARTMAN’s success.
  • Virtually everyone relied on a combination of vacuum suction and grippers to grab the objects. This is an area that all the teams told me that much work remains: picking up a stuffed plush toy, a soft packet of biscuits, a plastic bottle of mineral water, a crystal champagne flute, a packet of batteries or a softcover book vs. hardcover demands very different techniques and tools to ensure a reliable grip that neither damages the goods nor creates a risk of damage by dropping it accidentally – something that befell just about everyone at some point. The human mind, eyeball and hand and the way we grasp with it when it all works together is indeed a marvel that the brightest minds in the field still struggle to emulate.
  • This competition was MUCH closer than the final scores indicated: in the end, solid teamwork and a systems approach for ACRV got them over the line. In reality, the scores did not reflect how close many teams were, and how innovative a few approaches to AI and robotic vision were employed. Again, we come to the fact that this was an exercise in systems management: numerous separate concepts/ideas/technologies interacting to deliver outcomes in a fairly dynamic environment. However, it was pleasing to see that Amazon and other executives were looking at the individual technical strengths of all the teams.
  • In terms of robot articulation speed, we have great capability in that area now, even if it was not on display at the ARC. One team had individuals who had worked on a Staubli robot - demonstrated here  - that impressed. This clearly shows the speed of articulation possible, one that few humans could approach, and certainly none for any sustained period of time with any accuracy. But that alone is not enough. The Staubli robot has no real intelligence and its gripping solution only works on a very limited range of products.
  • The experts said that we should not hold out hope of a total “Eureka moment”: some miraculous, singular, transcendental breakthrough that somehow brings everything together. What now appears to be the winning combination is a fusion of technologies…and the hideously complex task of making them work together. There need to be developments across a chain of fields, which will happen over time, but there will need to be a lot of tireless work to turn them into a real solution.
  • A key focus needs to be sensor fusion (including stereoscopic [3D] vision, lasers for ranging, ultrasonics for shape confirmation and touch sensors) via Artificial Neural Networks, using a coding language which can fully leverage ANNs, giving the machine general intelligence and the ability to learn quickly, to infer from existing observations. General intelligence and automated reasoning are the ultimately desired capabilities being sought, though most of the teams stated that we could be further away from these goals than many think. I spoke to people at length about these technologies and the general message is the same: we need them to make this work, but they are proving far harder than we ever imagined.
  • There was comparative talk about the progress being made with driverless cars and on the road automation. It was surprising to hear many people who have work in Robotic Vision say that the challenges they face in getting a car to navigate a road safely pale into relative ease compared to getting an arm to pick up items in a tray.
  • The work of Google in the field was being discussed, as was that of IBM, Microsoft and other firms. But Google’s work was noted especially as being of a high order and of great interest to everyone in the competition.
  • This was especially intriguing: Amazon is exploring an entirely new area of knowledge focused around how humans and robots can optimally work together. It includes such aspects as task breakdown according to lean principles, safety standards and protocols, human psychology, learning and performance measurement. Whilst courses in this field are available from a number of Universities, Amazon feels its real world experience makes it an early expert whose knowledge is at the cutting edge.


Discussions with individuals familiar with the situation at Amazon FCs indicated that the ARC developments are in part designed to give the Amazon teams designing future generations of the Amazon FCs (in this case, the 9th generation) some idea of key features that will need to be incorporated into the layout of the FC to allow them to take advantage of the latest developments in robotics and associated technologies relevant to logistics.

Around 2014, it was expected that by 2018 when the 9th generation FC would be introduced, there would be significant developments in robotics that would permit closer interactions between humans and “fairly” autonomous robots. At present, this goal does not appear close to being met, at least not to the level initially expected. But the design of the FC proceeds. Thus, the 9th generation FC may represent less of a leap than was originally expected. There is apparently some debate happening in Amazon if it is worthwhile to delay introduction of a real 9th generation FC and wait until robotic technology allows for a real breakthrough that provides a clear advantage over the current generation. The outcome of this is debate not certain at this time.

Whatever the case may be, warehouse workers should breathe easier. They are not an endangered species.

Not even close, and for some time yet. Whilst many may dismiss Amazon’s claims that robots and humans work together better as simply sugar coating and placating people to the fact their jobs will eventually be done by robots, the reality is that Amazon has gone on a hiring spree for warehouse workers as full time employees, not temporary contractors. Eventually, this may cease…but the key word is “eventually”. And that could mean another decade away. Despite the incredible collection of intellect I have seen in robotics, we are yet to come close to replicating those skills that are needed in commercially viable, real world environment of picking and stowing. Whilst an official answer will not be provided, there is evidence that Amazon is moving towards a hybrid future of humans and robots working alongside each other in the FCs for much longer than originally thought required.

In the end, what happened at the ARC this year is a step towards a destination that is as inevitable as the timeline remains unpredictable. Of course, it is not something that will happen all at once , a “Day 0” where staff find out they have all been replaced by robots. It will be the case where robots will over time undertake more and more roles formally done by people. As to what happens to those people, that is a question that cannot be answered for some time to come.


Whilst I cannot readily see Amazon even start fully automating their warehouses for at least another seven years – and likely much longer – the process has commenced. It will, however, be a slow take-up…and in the meantime, there will be many more opportunities for humans to benefit by working with robots. The ARC demonstrated both the progress made – impressive in many ways – the limitations that still exist and the challenge that lies ahead…and what is will likely be a monumentally costly amount of research and development needed. The race to robotic automation is a marathon, not a sprint, with a timeline that will take longer – and involve far more cost and disappointment – than perhaps many envisaged a few years ago.

But what was clear is this: humans are still incredibly capable in many tasks that one would expect robotics should reign supreme. The human link between the eye, the brain and the hand offers system integration that our current best technologies are still struggling to approach, despite the large number of brilliant people working on the problem. The need for true general intelligence, automated reasoning, deep learning and a myriad of other breakthroughs that will likely depend on Artificial Neural Networks was made clear watching these robots try to perform tasks that human children could easily master. It will require time and huge financial resources, something that Amazon Robotics is already proving it is willing to do… as are many others.

But for now, Amazon Fulfillment Centers function at the limit of our best application of the technology, and the ARC provides a significant boost to help push the technology along just a bit faster – 2018 will be fascinating to watch.