January 9, 2025 • 32 mins
In this episode we sit down with Dr. Matthias Winkenbach, Director of Research at the MIT Center for Transportation & Logistics, Alejandro González, Software Business Unit Director at Mecalux, and Iñaki Fernández, Chief Technology Officer at Mecalux.
Mecalux, a provider of warehouse management solutions, is a founding research partner of the new MIT Intelligent Logistics Systems Lab, which is at the forefront of advancing logistics through innovative technology. We discuss how AI and machine learning are not just buzzwords but can actually create additional value in warehouse robotics, such as in the case of autonomous robots and software solutions that help companies manage demand out of a distributed network.
Host & Executive Producer: Benjy Kantor Marketing Writer & Producer: Mackenzie Berry Sound Editor: David Benjamin Sound Audio Engineer: Kurt Schneider
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
(00:00):
(bright music)
- Welcome to another episodeof "Supply Chain Frontiers,"
the MIT CTL podcast wherewe explore the latest trends
and innovations insupply chain management.
I'm your host, Benjy Kantor, and today,
I'm thrilled to welcomeback Dr. Matthias Winkenbach
MIT CTLs Director of Research,
and more pointedly, withregard to this episode,
the Director
of the brand new MIT IntelligentLogistics Systems Lab.
(00:23):
Matthias has been at theforefront of advancing logistics
through innovative technology,
and today, we'll delve deeper
into the partnership with Mecalux,
a provider of warehousemanagement solutions
and a founding research partner
of the Intelligent Logistics Systems Lab.
First, this episode of MIT"Supply Chain Frontiers"
is brought to you by the MITCenter for Transportation
and Logistics Executive Education Program.
(00:43):
Offered twice a year, January and June,
this program's designedfor corporate leaders
and aspiring executives insupply chain, logistics,
procurement, AI, and related fields.
It's open to learnersat every level focusing
on strategic skills and industry insights
that drive innovation and growth.
Instructors include expertsfrom CTL and across MIT.
Our next executive ed sessionis right around the corner.
(01:04):
To learn more, visitctl.mit.edu/executive-education.
Joining us on "SupplyChain Frontiers" today
are Alejandro González,
the Software BusinessUnit Director at Mecalux,
and his colleague,
Mecalux Chief TechnologyOfficer, Iñaki Fernández,
who are here to share insights
on how this collaboration aims
to transform logistics systemsand improve efficiency.
(01:25):
We'll discuss the futureof intelligent logistics
and how companies like Mecalux
are leveraging AI to enhancesupply chain operations.
Let's jump right in.
Well, thank you for joining me, everybody.
I really appreciate it.
Just to kind of followup on what we discussed
a couple months back, Matthias,
could you give a recap ofthe purpose of the ILS lab
and how it came to be?
(01:46):
- Sure, yeah, so I thinkas we discussed last time
when we spoke on this podcast,
we've been doing research
in the logistics and supply chain industry
for decades at CTL,
and we've mostly done it
from an operations research point of view.
So we used optimizationand simulation methods
for all sorts of differentprojects we're embarking on
with our research partners.
And lately, there's alot of hype, obviously,
(02:08):
around machine learning andartificial intelligence,
and sometimes you get the feeling
that people are just trying
to put a little bit of theAI sprinkle on everything
to make it more interesting.
And that's exactly whatwe did not want to do.
We wanted to actuallyhave a lab that works
with a credible industry partner
or actually a set ofcredible industry partners
(02:28):
on identifying actual use cases,
actual fields where AI can augment
what we've been doing so far
with purely operationsresearch focused methods.
So trying to identify use cases
in the logistics and supply chain industry
where AI and machine learningare not just a buzzword
but actually create additional value.
And that's a great fortune for us,
(02:48):
that with Mecalux, wefound a founding partner
who gave us the means toactually explore this,
because some of this boils down
to doing very fundamentalresearch at first,
research that may not immediately yield
commercially viable solutions,
but research that's necessary to then,
in subsequent iterationsof this collaboration,
yield to solutions thatcan actually be applied.
(03:10):
- And before we bringin Alejandro and Iñaki,
what prompted the collaborationspecifically with Mecalux?
- Well, I mean, whatprompted it was that actually
the CEO of Mecalux was listeningto a podcast of Mecalux
that I was a guest on acouple of months ago by now,
and I kind of expressed that idea
that rather than just following the hype,
we would want to see
(03:31):
what are the most useful application areas
of AI and machinelearning in our industry.
And I think that kind of got him excited.
That's why Mecalux reached out to us
to see whether we would be interested
in a research partnership.
And obviously, we were.
Fast forward to today, we are here.
We just kicked off thiscollaboration formally
and we're working on thefirst research project.
- The power of podcasts.
(03:51):
- Yes.- Can you believe it.
Well, Alejandro and Iñaki,
from the perspective of Mecalux,
what do you see as the keybenefits of the partnership here?
Why would a company likeyours get involved with CTL
and the work that Matthiasand his lab are doing
for your company and yourclients and the world at large?
- At Mecalux, we've beenin the logistics business
for a long time,
so we have a very deepunderstanding of how things work.
(04:12):
We believe that by combiningMIT's academic knowledge
with our own practicalreal world experience,
we aim to develop groundbreaking research
that will make a realdifference for our clients.
- Yes, and to complimentto what Iñaki was saying,
I think that one of the goals
is also to take these breakthroughs
in AI and robotics for example,
(04:32):
and roll out them acrossour customers warehouses
around the world,
and obviously, in aquick and efficient way.
So we're really focused
on trying to deliver tangible results
that our customers can benefit from.
- Great, I understandat the launch of this,
and Matthias and I were talking about this
in our last session,
but the lab has threesimultaneous research projects.
(04:53):
I know it's very early,
so to ask what's been done already
might be a little premature,
but what are the nextsteps there, Matthias?
- Yeah, I mean obviously we are
in this exploratory phase right now.
We just started working onthis a couple of weeks ago.
But broadly speaking, weare looking at two fields
that have an immediate impact,
not just on Mecalux's business
but also have an immediatecommercial impact
(05:15):
on any large scale logistics
and supply chain company out there.
One, is looking at warehouse robotics.
Warehouse robotics is an areawhere AI and machine learning
can actually, more or less,immediately be applied
to the real world.
Unlike areas like autonomous cars
or drones or what have you,
this is not an area where we'retalking about applications
(05:37):
that may or may notmaterialize in 5 or 10 years.
This is an area of application where
if we find a better solution,
we can actually try it outtoday in a real operation.
So what we are looking at there
is trying to make autonomous robots
that move around in warehouses
to, for instance, transportboxes or pallets from A to B
within the four walls of a warehouse,
(05:59):
trying to make those robots smarter.
In that sense, also makethem work more efficiently
together with human operators.
So make them more robust, for example,
against random interruptions.
Think of a human warehouse worker walking
in front of an autonomous robot.
Right now, that might shut down the robot
and basically harm theproductivity of that entire system.
(06:22):
We're trying to build algorithmswith which these robots
can navigate in a morehuman-like, more intelligent way
to basically increase overall productivity
of that warehouse system.
The other area of application
is more related to software solutions
that help companies manage demand
(06:42):
out of a distributed network.
So what does that mean?
So if you're for instance, a retailer
and you have a large,
potentially global network of warehouses,
fulfillment centers, retail stores,
all of which cantheoretically fulfill orders,
for instance, of your online customers.
So as soon as someoneplaces an order online,
(07:03):
just to stay within that example,you have to make a choice.
Like where do you fulfill that order from
and when do you fulfill it?
In which priority orderdo you fulfill orders?
And related to that is howdo you manage inventory?
Where do you keep your inventory
in such a distributed network
such that you can actuallyserve your customers
most reliably and most cost efficiently?
(07:23):
So these are very complexoptimization problems
to which our traditional domains
or operations research has only found,
let's say, approximate solutions.
We're hoping to combine
those existing methodologicalapproaches with newer methods,
machine learning methods thatactually make them smarter,
make them more data-driven,
help us make these decisions
(07:43):
in a better, more efficient way.
And the benefit of that could be manyfold.
It could obviously be commercial benefits
like reduced costs,
but also social andenvironmental benefits.
So for instance, thebetter we manage this,
the less unnecessarytransportation might be happening
in our network.
So the fewer unnecessary emissions.
(08:04):
And similarly, if wemanage this really well,
we can reduce waste.
So there's many possiblebenefits of doing this right.
And that's why we are soexcited about working on this.
- The first part of your answerwas reminding me of a story
from a presentation fromone of our colleagues,
Dr. Miguel Rodriguez Garcia,
who works with our MicroMasters program,
who also works with robots and warehouses.
And he was telling a story
(08:25):
about how this completelyefficiently built warehouse
where two robots smashed into each other,
started a fire and theentire warehouse burned down.
So other than that sort of practical,
wanting to avoid that kind of situation,
what do you see, Iñaki and Alejandro,
as the key benefits for this partnership?
Why do these projects matter to Mecalux?
- So they three research projects
(08:46):
that we will develop togetherwith MIT are key for us.
So when it comes to AMRs,
AMRs stands for autonomous mobile robots.
They are becoming increasinglypopular in warehouses,
to the flexibility they provide.
They make it easy to scaleoperations and respond to changes
and demand by adding more robots.
So this design of research with MIT
(09:07):
will help us create a newgeneration of AI-powered AMRs
that outpace the performanceof today's market options.
With reinforcement learning,
we can actually maximizethis machine's productivity
in warehouses and actuallydriving greater efficiency.
- Then going to thesoftware side of things,
at Mecalux, part of our DNA,it's obviously innovation.
(09:28):
So we really believe thatinnovation is extremely needed
to be able to provide the bestsolutions for our customers.
And this is why we havea large team of engineers
at this moment working constantly
on innovating andimproving the capabilities
of our logistics software.
And through the jointsoftware focus research lines,
(09:49):
in the end, we aim toharness AI's potential
so that the models can self-train
and learn from past experiences.
And this self-improving AI will ensure,
for sure, a maximumproductivity in warehouses
and will integrate thesebreakthroughs into our software.
So helping, in the end,
our companies to establishdistribution strategies
(10:11):
that dynamically adapt tothe environmental demands
through the AI.
- Well, you've mentioned technology
and innovation a few times,
and with that kind of in mind, Matthias,
I guess this question is for you,
how is the lab initially leveraging AI
and machine learning inthe research process?
- So we obviously can't go
(10:31):
into the methodological details here,
but the general idea is that we're trying
to improve our systems that already exist.
Both those autonomous mobile robots
that we've been talking about,
as well as the software that manages,
for instance, online orders in a network.
These solutions already exist.
Today, they are performing
predominantly based on predefined rules.
(10:54):
So some human developer atsome point had a good idea
and wrote down a bunch ofrules by which, for instance,
the robots decide how tonavigate through a warehouse
or by which distributed ordermanagement software decides
which facility should fulfill an order.
And these rules aregenerally doing a decent job,
but they're not perfect.
(11:14):
So the first step thatwe're trying to achieve here
is we're trying to calibrate our solution
against the status quo.
So in a way, we're tryingto imitate the behavior
of those human-defined rules
in a learning-based environment.
The first step is just trying
to establish a machinelearning model, for instance,
that can more or less replicate
(11:36):
what the current systems are doing,
because that's kind ofour performance baseline,
what we want to compare ourselves against.
Then in the second step, wetry to improve over this.
So Iñaki mentioned reinforcement learning.
There's a variety of differentmethodological approaches
that we could choose here,
reinforcement learning is one of them,
but the idea basically isstart off that baseline
(11:57):
that mimics the status quo
and try to make thesesystems improve over time.
So for instance,
we try to make the robotlearn from experience
and learn from previousnavigational choices
that might have led tosuboptimal outcomes.
So for instance, it chose to turn left,
but unfortunately got stuckin a cul-de-sac, for example.
But giving those machines theability actually to reflect
(12:20):
on their behavior,
reflect on the performancethat they get from it,
and try to improve next time.
- Like a parent, I'mtalking to my 6-year-old,
and I said, "I want you tothink about what you've done."
- And kind of the othernice concept behind this
is that if we are in a rule-based world,
whoever designed those rules,
designed them with acertain objective in mind,
but was actually neverreally able to kind of prove
(12:43):
that the rules that that person defined
would actually, for instance,
lead to the optimal costperformance of the system.
Now that we're in alearning-based environment,
we can actually definewhat our objective is
and that objective mightalso be much more complex
than just minimizing cost
or maximizing lead time or whatever.
We can basically definewhatever objective we wanna have
(13:04):
and let those systemslearn the best behavior,
the best policy to achievethe best possible outcome
along that objective.
And that's something that existing methods
basically can't really do
and that's why we're usingmachine learning methods
to add that capability.
- And are there existing technologies
that Mecalux is already using
that you're integrating intoyour research or planning to?
(13:27):
- Well, in a sense.
So as I said before,
we are trying to mimicthe status quo first.
So for instance, to stick with the robots,
we're obviously using the robot solutions
that Mecalux is buildingand selling to its customers
as kind of the technology baseline.
So these are the vehicles thatwe're trying to work with.
These are the vehiclesthat we're trying to model
(13:47):
and simulate and hopefully, improve.
And we're also obviouslyusing the existing software
that makes these machinesthink as our baseline.
So the current rules bywhich these machines navigate
through a warehouse, that'swhat we are building off of.
In the long run, obviously,some of our research may
in turn be reintegratedinto these machines
(14:09):
if we can show that our methods,
our models can actually outperform
what is currently being done.
- Similarly for you, Iñaki and Alejandro,
is Mecalux thinking so far aheadin the idea of the findings
of this research actually being integrated
into Mecalux business solutions
and what is the thinking beyond that?
- Yeah, so short answer is yes,
(14:30):
but let me develop that a little bit.
So while our softwareautomation and robotic systems
are constantly evolving
because obviously, we needto follow what our customers
in the end need,
we aim to take them to a step farther
by integrating MIT'sdiscoveries into our technology.
And at Mecalux, we are awareto stay at the forefront
(14:52):
of logistics innovation,it is obviously essential
to continuously adopt the breakthroughs
in the science and engineering.
And this is why we believethat MIT's pioneering research
will help us to develop a new generation
of logistics technologies
that go beyond justefficiency and productivity.
(15:12):
So they will truly transformhow goods are stored, moved,
and managed, and notonly within the warehouse
but also outside the warehouse
and more talking aboutsupply chain networks,
which is also one of thetopics that we wanna address.
- So we have high expectationson this collaboration.
We hope to fully leverageAI and machine learning
(15:33):
to give our customers asignificant competitive advantage.
With MIT's support, wewill be able to push
the limit of these technologies
from finding demand forecasting
to developing smarter, fasterwarehousing operations.
So integrating researchoutcomes into our product will,
(15:53):
I'm sure, it allow us to offeradvanced predictabilities
that anticipate our customers'challenges and needs.
- And I'm glad you brought up that point
'cause it's an interesting challenge
from a practical standpoint.
What are the biggest challenges?
How do you actually practicallyintegrate this research
and advanced technologies in general
into your traditional logistics processes?
(16:16):
- So one of the biggestchallenges that we face
in integrating advanced technologies
into our traditional logistics
is the balance that always exists
between innovation and practicality.
So many warehouses still relyon long established processes,
sometimes even manual ones,
and that have served them for decades.
(16:37):
But bringing newtechnology like automation,
like advanced warehousemanagement systems,
dumb softwares with sophisticationof order orchestration,
inventory optimization,
all of this together obviouslyrequires a mindset shift,
and sometimes a complete rethinking
of the workflows of the warehouse
and how their supply chain operates.
(16:58):
So this is one challenge then,another one is adaptation.
It's also one of the challengesthat we most commonly see
in our customers,
because for some clients,
the shift from traditional methods
to something like what we aretrying to do in this program,
which is AI-driven inventory management
can seem a little bitdaunting, but at Mecalux-
(17:19):
- Just a little, just a little bit.
Yeah. (giggling)- Yeah.
But at Mecalux, we try to invest heavily
in designing user-friendly interfaces
and providing hands-on trainingand support to our customers
to help them to ease thistransition throughout the years
and throughout the use of our technology.
And last but not least,
I think that as technologykeeps progressing,
(17:42):
so do the expectationsaround speed, accuracy,
and data insights.
So we are constantly innovatingand refining our solutions
to stay ahead of market demands.
For example, we are focused
on making our systems more adaptable,
scalable but responsive at the same time
so that they can growwith our clients' needs
(18:03):
and future proof of their operations.
- What are the hesitationsfor adopting new technologies
within supply chains?
Is that something Mecalux experienced,
like a hesitation or a sensitivity to it?
If so, how do you overcomea resistance, I guess,
internally with staff fromthe top all the way down
with communicating that kind of decision
to overcome the resistance tointegrating new technologies?
(18:27):
- That's a great question, Benjy.
There are severalreasons why organizations
might be hesitant toadapt new technologies
within their supply chains.
But one of the most common reasons
is simply challenge of change.
Especially in the field like logistics
where traditional methods havebeen reliable for decades,
(18:47):
we have many customers worriedthat adopting new technology
will disrupt their operationsor lead to costly downtime.
At Mecalux, we have systems in place
to ensure a smoothtransition to new technology.
For example, one of our recent projects,
we automated IKEA's components warehouse
without disrupting ongoing operations.
(19:09):
Their specific requirement
was to implement automated systems
without altering the warehouse structure
or holding operations.
That was a mass requirement.
And the project was a success
and has boosted logistics efficiency.
Now, they fulfill 99%of the orders on time
and in full thanks to automation.
- To build on that,
I think what it essentiallyboils down to is trust.
(19:29):
And that's probably the biggest challenge
when you think about machine learning
and artificial intelligencecompared to traditional methods
that have been used in the supply chain
and logistics industry.
Because at the end of the day,
most machine learningmethods are a black box,
not just to practitioners,even to researchers.
We don't exactly know howsuch a model will respond.
(19:50):
So to give a very tangible example,
if you have a robot movingaround the warehouse,
and so far it's beencontrolled by a set of rules.
One of those rules might be
if you get closer than halfa meter from something else,
slow down.
And you can see that rulein the code of the software
that controls that robot,
so you know exactlythat that's the behavior
(20:12):
that you're going to seeif that robot comes close
to something that might be dangerous.
In the machine learning model,doing the exact same thing,
you don't see that anymore.
There is no if then elsestatement that says,
"If X happens then do Y."
You're basically trustingthat the model learned
that this is the desired behavior,
but you have no guarantee,black and white, in code,
(20:35):
that would tell you thisis exactly how the robot
is going to behave.
So this is just a made up simple example,
but it comes down to whether it's safety,
whether it's business continuity,
whether it's all sorts of risk associated
to integrating so-called smart systems
in a logistics network,in a logistics facility.
You have to build trustthat it will behave the way
(20:58):
that it's intended to behave.
And that is probably the biggest hurdle
that we currently see froma research point of view,
not just with Mecalux butwith all of our research,
that this transitiontowards models and methods
that are no longer humanexplainable, necessarily,
is a big mental shift.
- With your example,
this is maybe perhaps gettingin the weeds a little bit,
but how do you build inthat quality assurance
(21:18):
where, like if I'm justusing generative AI
to help me write a paperor write an article,
I can then read through it pretty quickly,
see where the correctionsneed to be made and that,
but if you're talkingabout the safety issue
where you're expectingthat the robot knows
that it's not supposed togo, how do you test that?
How do you, in a real life scenario?
- Yeah, I mean ideally,you wanna not test it
(21:40):
in a real life scenario first.- Yeah, good point.
- Even though that's wherewe wanna go to, obviously.
But, so for instance,one of the first things
that we are currently doingin this research collaboration
is building out a verydetailed simulation test bed
so that we can actually mimicthe real world operations
of any warehouse that we mighthave out there virtually,
build almost like avirtual twin of a warehouse
(22:03):
so that we can throw anykind of new algorithm at that
and see how, in this case,the robots would behave.
Obviously, the challenge here
is to model the simulation test bed
as accurately as possible
so that we can depictall the possible things
that might go wrong in the real world.
And to be honest, we'll never get there,
we'll never get to 100%
(22:24):
of the true complexity of a warehouse.
But we wanna get to, let'ssay a confidence level
where we're like, okay,
we are sure enough about this algorithm,
now, we can actually testit in the real world.
Now, we can actually deploy this
to a pilot warehouse of somecustomer and see what happens.
And obviously, we wanna start small there,
test it out at a small scale
(22:44):
so that if something doesn'tbehave the way it should,
we can immediately interveneand the damage is limited.
But that's typically how this goes.
You first virtually test it,
then you do a smallscale real world pilot,
and then hopefully, everything pans out
and you can roll it out at scale.
- And I don't think I'm late to the game
in saying this theme ofthe importance of trust
when it comes to AI isgonna be just a growing
(23:06):
and growing theme.
And probably, it is already in academia,
but like I know that ourcolleague, Bryan Reamer,
with the Advanced VehicleTechnology Consortium
has been talking about,
like this is the only way
that we're gonna get movement on this,
when there is public trust.
But it seems like there is some level
of corporate trust here on Mecalux's side
for when you're putting forth that,
and high expectations
for when the IntelligentLogistics Assistance Lab
(23:28):
is producing some research.
So I guess for all of you, giventhat the trust exists there
or that you're trying to establish this,
how do you envision thispartnership between CTL
and the lab and Mecaluxinfluencing the future landscape
of supply chain management,of warehouse management,
things like that?
- So ultimately, our missionis to help, as I said before,
(23:48):
companies to achieveoperational excellence.
Whether it's AI, robotics,
or smart warehouse management systems,
or even distributedorder management systems,
we're constantly looking fornew ways to help our clients
to optimize their operations
and therefore be able tobetter utilize their resources
and save time and cost,
(24:09):
which is in the end, themain goal of every company.
So by this collaboration with MIT,
what we wanna do is that wewant to push the boundaries
of what's possible inthe logistics technology.
And we envision thatthis partnership leading
to breakthroughs in areaslike AI-driven automation,
predictive analytics, andsmart inter-logistics robots,
(24:31):
which we can then integrateinto our solutions
to help in the end, companies to operate
with a whole new level ofefficiency and productivity.
- We strongly believe thatthis research partnership
with MIT and with Matthias' team
will bring in the best andmost advanced technologies
to help managers make logisticsprocesses more efficient.
(24:53):
For example, with AI-enabled systems,
we can empower clientsto anticipate issues
before they arise.
They will be able tooptimize resource allocation
in real time and and makefaster data-driven decisions.
- If I may add to this.- Please.
- So obviously, you might ask,
well, we have, to some extent at least,
self-driving cars out there on the road.
(25:14):
We have companies that fly rockets
to space using machinelearning and AI to some extent,
I would assume.
So why does the logisticsindustry still not know
how to operate robots intelligently?
And I think the answer to that
is that the logisticsand supply chain industry
is notoriously risk averse,
(25:35):
which kind of relates towhat we discussed earlier
about that trust issue.
And also supply chainlogistics traditionally
has been very much focused on cost,
on very short term returns on investments.
And that's honestly oneof the main challenges
that we were facing in recent years
when we were looking for partners
(25:56):
to actually help us getthis type of research
off the ground.
Because it's not like the industry
didn't see the potentialvalue of these methods,
but the fact that it mighttake a couple of years
until we actually seesolutions emerge from this
that really turn the needlein terms of cost efficiency
or whatever the metric might be.
(26:17):
And the fact that we'retalking about methods
that may, at leastinitially, behave differently
from what we were expectingthem to behave like,
that usually turned a lotof traditional logistics,
supply chain management companies away
or basically made them not interested
in investing into researchand development in this space.
(26:38):
And that's why for us, it's such a fortune
that with Mecalux we found a partner
who was willing to takethat leap of faith,
both in terms of trusting the solution
and in terms of allowing us to experiment,
allowing us to build the foundations
without an immediate need
for a positive return on that investment.
(27:01):
- Well, let's talk a littlebit about that investment
or those expectations, I guess,which is, my understanding
is that this is an initialfive-year partnership
between CTL and the lab and Mecalux.
What are the hopes for the benchmarks
that you will see over those five years?
I don't know how concreteor ethereal they are.
Is it after year one,we're going to have X,
after year two, we're gonnahave Y, that kind of thing?
- I mean that's hard to predict.
(27:22):
Honestly, my main hopefor this is, first of all,
that this research collaboration
will be a little bit of a trailblazer,
if that's the right Englishword to use, I don't know, but-
- Makes sense to me. (giggles)
I've spoken English all my life.
- By the means given to usthrough this partnership,
we can show that AI and machine learning
is not just a buzzword,a little bit of sprinkle,
and at the end of theday, it's overly hyped,
(27:45):
but that we can actuallycome up with solutions
that are trustworthyand make economic sense,
make practical sense, make also sense
from an environmental,social point of view.
So basically make sense alongall the possible dimensions
along which we want
to optimize the futurelogistics systems out there.
And once we can show this,
(28:05):
we hope that this resistancethat I was describing earlier
of the logistics and supplychain industry as a whole
towards this type ofinnovation will slowly reduce
and we'll see more and more engagement
from a larger part of theindustry in academic research
that might hopefully bringthe logistics industry
back on track comparedto other industries.
(28:27):
And the other thing that very practically
that I hope to see from this partnership
is that we get to try outthings in the real world.
Because very often in academia,
you are a little bit in a weird situation
where you come up with super cool methods,
super powerful models,
you think you invented thebest thing since sliced bread,
(28:47):
and then no one is willingto actually try it out
in real life.
And here this partnership,I think we are at a point
where we want to try thisout in the real world.
And that's, for me, I wouldbe very happy if let's say,
in a year from now, wewould see some robots moving
around the warehousethat are actually powered
by some of the work that we do here.
(29:08):
- I'm sure we will.
- Yeah, I guess for Mecalux's guess,
like how do you see therole of what's happening,
not just here, but herein terms of the research
on the logistics side of thingsover the next five years,
but the other things thatMecalux is investing in.
Like how do you see theadvent of new technologies
being part of what you'redoing over the next few years?
- So over the next 5 to 10 years,
(29:29):
we see logistics continuing to transform
from a traditional support function
into a strategic driverof business growth.
Technologies like AI, machine learning,
productive analytics willplay a huge role on this.
They will enable moreprecise demand forecasting,
optimize inventory management,
and actually smarter decision-making
(29:52):
across the supply chain.
- And adding something towhat Iñaki has already said,
so we also foresee strongtrends in the market
towards greater automationand robots in warehouses.
So automation will nolonger be just an option
for large scale operations,
especially when we're talking
about smart inter-logisticsrobots like the AMRs.
(30:14):
So this is a really good way for companies
to make their first step with automation,
probably with affordable investments.
So it's gonna become more accessible
and essential for businesses of all sizes.
And what we've seen with labor shortages
and the need of faster turnaround times,
(30:34):
automation and digitization
and also the applicationof AI in all of this
will for sure play a key role
and it's gonna be really, really important
to meet customer expectationsin terms of speed,
accuracy, and flexibility.
(bright music)
- Thank you, this hasbeen the 31st episode
(30:54):
of "Supply Chain Frontiers."
We appreciate you joining us.
We appreciate the insights shared today
by Dr. Matthias Winkenbach of MIT CTL,
and our guests, Alejandro González
and Iñaki Fernández from Mecalux.
As we continue to explore
the intersection oftechnology in logistics,
it's clear that partnerships like these
are paving the way for a smarter
and more efficient supply chain landscape.
(31:15):
(bright music)
I'm not only fortunate enough
to host "Supply Chain Frontiers,"
but on this episode, I'mthe producer as well.
Our sound editor is DaveLashinsky of David Benjamin Sound.
Our audio engineer today
is Kurt Schneider of MITAudio Visual Services.
MIT "Supply Chain Frontiers"is recorded on the MIT campus
in Cambridge, Massachusetts.
Be sure to check out ourprevious episode with Matthias
(31:35):
for more context on this partnership.
And stay tuned for our nextepisode where we'll continue
to delve into the innovationsshaping the future
of supply chain management.
You can hear all episodesat ctl.mit.edu/podcasts
or search "Supply Chain Frontiers"
on your preferred pod host.
Until next time, onbehalf of the researchers,
instructors, staff and partners
here at the MIT Center forTransportation and Logistics,
(31:58):
I'm Benjy Kantor andthank you for listening.
(bright music)
(bright music)
- Welcome to another episodeof "Supply Chain Frontiers,"
the MIT CTL podcast wherewe explore the latest trends
and innovations insupply chain management.
I'm your host, Benjy Kantor, and today,
I'm thrilled to welcomeback Dr. Matthias Winkenbach
MIT CTLs Director of Research,
and more pointedly, withregard to this episode,
the Director
of the brand new MIT IntelligentLogistics Systems Lab.
(00:23):
Matthias has been at theforefront of advancing logistics
through innovative technology,
and today, we'll delve deeper
into the partnership with Mecalux,
a provider of warehousemanagement solutions
and a founding research partner
of the Intelligent Logistics Systems Lab.
First, this episode of MIT"Supply Chain Frontiers"
is brought to you by the MITCenter for Transportation
and Logistics Executive Education Program.
(00:43):
Offered twice a year, January and June,
this program's designedfor corporate leaders
and aspiring executives insupply chain, logistics,
procurement, AI, and related fields.
It's open to learnersat every level focusing
on strategic skills and industry insights
that drive innovation and growth.
Instructors include expertsfrom CTL and across MIT.
Our next executive ed sessionis right around the corner.
(01:04):
To learn more, visitctl.mit.edu/executive-education.
Joining us on "SupplyChain Frontiers" today
are Alejandro González,
the Software BusinessUnit Director at Mecalux,
and his colleague,
Mecalux Chief TechnologyOfficer, Iñaki Fernández,
who are here to share insights
on how this collaboration aims
to transform logistics systemsand improve efficiency.
(01:25):
We'll discuss the futureof intelligent logistics
and how companies like Mecalux
are leveraging AI to enhancesupply chain operations.
Let's jump right in.
Well, thank you for joining me, everybody.
I really appreciate it.
Just to kind of followup on what we discussed
a couple months back, Matthias,
could you give a recap ofthe purpose of the ILS lab
and how it came to be?
(01:46):
- Sure, yeah, so I thinkas we discussed last time
when we spoke on this podcast,
we've been doing research
in the logistics and supply chain industry
for decades at CTL,
and we've mostly done it
from an operations research point of view.
So we used optimizationand simulation methods
for all sorts of differentprojects we're embarking on
with our research partners.
And lately, there's alot of hype, obviously,
(02:08):
around machine learning andartificial intelligence,
and sometimes you get the feeling
that people are just trying
to put a little bit of theAI sprinkle on everything
to make it more interesting.
And that's exactly whatwe did not want to do.
We wanted to actuallyhave a lab that works
with a credible industry partner
or actually a set ofcredible industry partners
(02:28):
on identifying actual use cases,
actual fields where AI can augment
what we've been doing so far
with purely operationsresearch focused methods.
So trying to identify use cases
in the logistics and supply chain industry
where AI and machine learningare not just a buzzword
but actually create additional value.
And that's a great fortune for us,
(02:48):
that with Mecalux, wefound a founding partner
who gave us the means toactually explore this,
because some of this boils down
to doing very fundamentalresearch at first,
research that may not immediately yield
commercially viable solutions,
but research that's necessary to then,
in subsequent iterationsof this collaboration,
yield to solutions thatcan actually be applied.
(03:10):
- And before we bringin Alejandro and Iñaki,
what prompted the collaborationspecifically with Mecalux?
- Well, I mean, whatprompted it was that actually
the CEO of Mecalux was listeningto a podcast of Mecalux
that I was a guest on acouple of months ago by now,
and I kind of expressed that idea
that rather than just following the hype,
we would want to see
(03:31):
what are the most useful application areas
of AI and machinelearning in our industry.
And I think that kind of got him excited.
That's why Mecalux reached out to us
to see whether we would be interested
in a research partnership.
And obviously, we were.
Fast forward to today, we are here.
We just kicked off thiscollaboration formally
and we're working on thefirst research project.
- The power of podcasts.
(03:51):
- Yes.- Can you believe it.
Well, Alejandro and Iñaki,
from the perspective of Mecalux,
what do you see as the keybenefits of the partnership here?
Why would a company likeyours get involved with CTL
and the work that Matthiasand his lab are doing
for your company and yourclients and the world at large?
- At Mecalux, we've beenin the logistics business
for a long time,
so we have a very deepunderstanding of how things work.
(04:12):
We believe that by combiningMIT's academic knowledge
with our own practicalreal world experience,
we aim to develop groundbreaking research
that will make a realdifference for our clients.
- Yes, and to complimentto what Iñaki was saying,
I think that one of the goals
is also to take these breakthroughs
in AI and robotics for example,
(04:32):
and roll out them acrossour customers warehouses
around the world,
and obviously, in aquick and efficient way.
So we're really focused
on trying to deliver tangible results
that our customers can benefit from.
- Great, I understandat the launch of this,
and Matthias and I were talking about this
in our last session,
but the lab has threesimultaneous research projects.
(04:53):
I know it's very early,
so to ask what's been done already
might be a little premature,
but what are the nextsteps there, Matthias?
- Yeah, I mean obviously we are
in this exploratory phase right now.
We just started working onthis a couple of weeks ago.
But broadly speaking, weare looking at two fields
that have an immediate impact,
not just on Mecalux's business
but also have an immediatecommercial impact
(05:15):
on any large scale logistics
and supply chain company out there.
One, is looking at warehouse robotics.
Warehouse robotics is an areawhere AI and machine learning
can actually, more or less,immediately be applied
to the real world.
Unlike areas like autonomous cars
or drones or what have you,
this is not an area where we'retalking about applications
(05:37):
that may or may notmaterialize in 5 or 10 years.
This is an area of application where
if we find a better solution,
we can actually try it outtoday in a real operation.
So what we are looking at there
is trying to make autonomous robots
that move around in warehouses
to, for instance, transportboxes or pallets from A to B
within the four walls of a warehouse,
(05:59):
trying to make those robots smarter.
In that sense, also makethem work more efficiently
together with human operators.
So make them more robust, for example,
against random interruptions.
Think of a human warehouse worker walking
in front of an autonomous robot.
Right now, that might shut down the robot
and basically harm theproductivity of that entire system.
(06:22):
We're trying to build algorithmswith which these robots
can navigate in a morehuman-like, more intelligent way
to basically increase overall productivity
of that warehouse system.
The other area of application
is more related to software solutions
that help companies manage demand
(06:42):
out of a distributed network.
So what does that mean?
So if you're for instance, a retailer
and you have a large,
potentially global network of warehouses,
fulfillment centers, retail stores,
all of which cantheoretically fulfill orders,
for instance, of your online customers.
So as soon as someoneplaces an order online,
(07:03):
just to stay within that example,you have to make a choice.
Like where do you fulfill that order from
and when do you fulfill it?
In which priority orderdo you fulfill orders?
And related to that is howdo you manage inventory?
Where do you keep your inventory
in such a distributed network
such that you can actuallyserve your customers
most reliably and most cost efficiently?
(07:23):
So these are very complexoptimization problems
to which our traditional domains
or operations research has only found,
let's say, approximate solutions.
We're hoping to combine
those existing methodologicalapproaches with newer methods,
machine learning methods thatactually make them smarter,
make them more data-driven,
help us make these decisions
(07:43):
in a better, more efficient way.
And the benefit of that could be manyfold.
It could obviously be commercial benefits
like reduced costs,
but also social andenvironmental benefits.
So for instance, thebetter we manage this,
the less unnecessarytransportation might be happening
in our network.
So the fewer unnecessary emissions.
(08:04):
And similarly, if wemanage this really well,
we can reduce waste.
So there's many possiblebenefits of doing this right.
And that's why we are soexcited about working on this.
- The first part of your answerwas reminding me of a story
from a presentation fromone of our colleagues,
Dr. Miguel Rodriguez Garcia,
who works with our MicroMasters program,
who also works with robots and warehouses.
And he was telling a story
(08:25):
about how this completelyefficiently built warehouse
where two robots smashed into each other,
started a fire and theentire warehouse burned down.
So other than that sort of practical,
wanting to avoid that kind of situation,
what do you see, Iñaki and Alejandro,
as the key benefits for this partnership?
Why do these projects matter to Mecalux?
- So they three research projects
(08:46):
that we will develop togetherwith MIT are key for us.
So when it comes to AMRs,
AMRs stands for autonomous mobile robots.
They are becoming increasinglypopular in warehouses,
to the flexibility they provide.
They make it easy to scaleoperations and respond to changes
and demand by adding more robots.
So this design of research with MIT
(09:07):
will help us create a newgeneration of AI-powered AMRs
that outpace the performanceof today's market options.
With reinforcement learning,
we can actually maximizethis machine's productivity
in warehouses and actuallydriving greater efficiency.
- Then going to thesoftware side of things,
at Mecalux, part of our DNA,it's obviously innovation.
(09:28):
So we really believe thatinnovation is extremely needed
to be able to provide the bestsolutions for our customers.
And this is why we havea large team of engineers
at this moment working constantly
on innovating andimproving the capabilities
of our logistics software.
And through the jointsoftware focus research lines,
(09:49):
in the end, we aim toharness AI's potential
so that the models can self-train
and learn from past experiences.
And this self-improving AI will ensure,
for sure, a maximumproductivity in warehouses
and will integrate thesebreakthroughs into our software.
So helping, in the end,
our companies to establishdistribution strategies
(10:11):
that dynamically adapt tothe environmental demands
through the AI.
- Well, you've mentioned technology
and innovation a few times,
and with that kind of in mind, Matthias,
I guess this question is for you,
how is the lab initially leveraging AI
and machine learning inthe research process?
- So we obviously can't go
(10:31):
into the methodological details here,
but the general idea is that we're trying
to improve our systems that already exist.
Both those autonomous mobile robots
that we've been talking about,
as well as the software that manages,
for instance, online orders in a network.
These solutions already exist.
Today, they are performing
predominantly based on predefined rules.
(10:54):
So some human developer atsome point had a good idea
and wrote down a bunch ofrules by which, for instance,
the robots decide how tonavigate through a warehouse
or by which distributed ordermanagement software decides
which facility should fulfill an order.
And these rules aregenerally doing a decent job,
but they're not perfect.
(11:14):
So the first step thatwe're trying to achieve here
is we're trying to calibrate our solution
against the status quo.
So in a way, we're tryingto imitate the behavior
of those human-defined rules
in a learning-based environment.
The first step is just trying
to establish a machinelearning model, for instance,
that can more or less replicate
(11:36):
what the current systems are doing,
because that's kind ofour performance baseline,
what we want to compare ourselves against.
Then in the second step, wetry to improve over this.
So Iñaki mentioned reinforcement learning.
There's a variety of differentmethodological approaches
that we could choose here,
reinforcement learning is one of them,
but the idea basically isstart off that baseline
(11:57):
that mimics the status quo
and try to make thesesystems improve over time.
So for instance,
we try to make the robotlearn from experience
and learn from previousnavigational choices
that might have led tosuboptimal outcomes.
So for instance, it chose to turn left,
but unfortunately got stuckin a cul-de-sac, for example.
But giving those machines theability actually to reflect
(12:20):
on their behavior,
reflect on the performancethat they get from it,
and try to improve next time.
- Like a parent, I'mtalking to my 6-year-old,
and I said, "I want you tothink about what you've done."
- And kind of the othernice concept behind this
is that if we are in a rule-based world,
whoever designed those rules,
designed them with acertain objective in mind,
but was actually neverreally able to kind of prove
(12:43):
that the rules that that person defined
would actually, for instance,
lead to the optimal costperformance of the system.
Now that we're in alearning-based environment,
we can actually definewhat our objective is
and that objective mightalso be much more complex
than just minimizing cost
or maximizing lead time or whatever.
We can basically definewhatever objective we wanna have
(13:04):
and let those systemslearn the best behavior,
the best policy to achievethe best possible outcome
along that objective.
And that's something that existing methods
basically can't really do
and that's why we're usingmachine learning methods
to add that capability.
- And are there existing technologies
that Mecalux is already using
that you're integrating intoyour research or planning to?
(13:27):
- Well, in a sense.
So as I said before,
we are trying to mimicthe status quo first.
So for instance, to stick with the robots,
we're obviously using the robot solutions
that Mecalux is buildingand selling to its customers
as kind of the technology baseline.
So these are the vehicles thatwe're trying to work with.
These are the vehiclesthat we're trying to model
(13:47):
and simulate and hopefully, improve.
And we're also obviouslyusing the existing software
that makes these machinesthink as our baseline.
So the current rules bywhich these machines navigate
through a warehouse, that'swhat we are building off of.
In the long run, obviously,some of our research may
in turn be reintegratedinto these machines
(14:09):
if we can show that our methods,
our models can actually outperform
what is currently being done.
- Similarly for you, Iñaki and Alejandro,
is Mecalux thinking so far aheadin the idea of the findings
of this research actually being integrated
into Mecalux business solutions
and what is the thinking beyond that?
- Yeah, so short answer is yes,
(14:30):
but let me develop that a little bit.
So while our softwareautomation and robotic systems
are constantly evolving
because obviously, we needto follow what our customers
in the end need,
we aim to take them to a step farther
by integrating MIT'sdiscoveries into our technology.
And at Mecalux, we are awareto stay at the forefront
(14:52):
of logistics innovation,it is obviously essential
to continuously adopt the breakthroughs
in the science and engineering.
And this is why we believethat MIT's pioneering research
will help us to develop a new generation
of logistics technologies
that go beyond justefficiency and productivity.
(15:12):
So they will truly transformhow goods are stored, moved,
and managed, and notonly within the warehouse
but also outside the warehouse
and more talking aboutsupply chain networks,
which is also one of thetopics that we wanna address.
- So we have high expectationson this collaboration.
We hope to fully leverageAI and machine learning
(15:33):
to give our customers asignificant competitive advantage.
With MIT's support, wewill be able to push
the limit of these technologies
from finding demand forecasting
to developing smarter, fasterwarehousing operations.
So integrating researchoutcomes into our product will,
(15:53):
I'm sure, it allow us to offeradvanced predictabilities
that anticipate our customers'challenges and needs.
- And I'm glad you brought up that point
'cause it's an interesting challenge
from a practical standpoint.
What are the biggest challenges?
How do you actually practicallyintegrate this research
and advanced technologies in general
into your traditional logistics processes?
(16:16):
- So one of the biggestchallenges that we face
in integrating advanced technologies
into our traditional logistics
is the balance that always exists
between innovation and practicality.
So many warehouses still relyon long established processes,
sometimes even manual ones,
and that have served them for decades.
(16:37):
But bringing newtechnology like automation,
like advanced warehousemanagement systems,
dumb softwares with sophisticationof order orchestration,
inventory optimization,
all of this together obviouslyrequires a mindset shift,
and sometimes a complete rethinking
of the workflows of the warehouse
and how their supply chain operates.
(16:58):
So this is one challenge then,another one is adaptation.
It's also one of the challengesthat we most commonly see
in our customers,
because for some clients,
the shift from traditional methods
to something like what we aretrying to do in this program,
which is AI-driven inventory management
can seem a little bitdaunting, but at Mecalux-
(17:19):
- Just a little, just a little bit.
Yeah. (giggling)- Yeah.
But at Mecalux, we try to invest heavily
in designing user-friendly interfaces
and providing hands-on trainingand support to our customers
to help them to ease thistransition throughout the years
and throughout the use of our technology.
And last but not least,
I think that as technologykeeps progressing,
(17:42):
so do the expectationsaround speed, accuracy,
and data insights.
So we are constantly innovatingand refining our solutions
to stay ahead of market demands.
For example, we are focused
on making our systems more adaptable,
scalable but responsive at the same time
so that they can growwith our clients' needs
(18:03):
and future proof of their operations.
- What are the hesitationsfor adopting new technologies
within supply chains?
Is that something Mecalux experienced,
like a hesitation or a sensitivity to it?
If so, how do you overcomea resistance, I guess,
internally with staff fromthe top all the way down
with communicating that kind of decision
to overcome the resistance tointegrating new technologies?
(18:27):
- That's a great question, Benjy.
There are severalreasons why organizations
might be hesitant toadapt new technologies
within their supply chains.
But one of the most common reasons
is simply challenge of change.
Especially in the field like logistics
where traditional methods havebeen reliable for decades,
(18:47):
we have many customers worriedthat adopting new technology
will disrupt their operationsor lead to costly downtime.
At Mecalux, we have systems in place
to ensure a smoothtransition to new technology.
For example, one of our recent projects,
we automated IKEA's components warehouse
without disrupting ongoing operations.
(19:09):
Their specific requirement
was to implement automated systems
without altering the warehouse structure
or holding operations.
That was a mass requirement.
And the project was a success
and has boosted logistics efficiency.
Now, they fulfill 99%of the orders on time
and in full thanks to automation.
- To build on that,
I think what it essentiallyboils down to is trust.
(19:29):
And that's probably the biggest challenge
when you think about machine learning
and artificial intelligencecompared to traditional methods
that have been used in the supply chain
and logistics industry.
Because at the end of the day,
most machine learningmethods are a black box,
not just to practitioners,even to researchers.
We don't exactly know howsuch a model will respond.
(19:50):
So to give a very tangible example,
if you have a robot movingaround the warehouse,
and so far it's beencontrolled by a set of rules.
One of those rules might be
if you get closer than halfa meter from something else,
slow down.
And you can see that rulein the code of the software
that controls that robot,
so you know exactlythat that's the behavior
(20:12):
that you're going to seeif that robot comes close
to something that might be dangerous.
In the machine learning model,doing the exact same thing,
you don't see that anymore.
There is no if then elsestatement that says,
"If X happens then do Y."
You're basically trustingthat the model learned
that this is the desired behavior,
but you have no guarantee,black and white, in code,
(20:35):
that would tell you thisis exactly how the robot
is going to behave.
So this is just a made up simple example,
but it comes down to whether it's safety,
whether it's business continuity,
whether it's all sorts of risk associated
to integrating so-called smart systems
in a logistics network,in a logistics facility.
You have to build trustthat it will behave the way
(20:58):
that it's intended to behave.
And that is probably the biggest hurdle
that we currently see froma research point of view,
not just with Mecalux butwith all of our research,
that this transitiontowards models and methods
that are no longer humanexplainable, necessarily,
is a big mental shift.
- With your example,
this is maybe perhaps gettingin the weeds a little bit,
but how do you build inthat quality assurance
(21:18):
where, like if I'm justusing generative AI
to help me write a paperor write an article,
I can then read through it pretty quickly,
see where the correctionsneed to be made and that,
but if you're talkingabout the safety issue
where you're expectingthat the robot knows
that it's not supposed togo, how do you test that?
How do you, in a real life scenario?
- Yeah, I mean ideally,you wanna not test it
(21:40):
in a real life scenario first.- Yeah, good point.
- Even though that's wherewe wanna go to, obviously.
But, so for instance,one of the first things
that we are currently doingin this research collaboration
is building out a verydetailed simulation test bed
so that we can actually mimicthe real world operations
of any warehouse that we mighthave out there virtually,
build almost like avirtual twin of a warehouse
(22:03):
so that we can throw anykind of new algorithm at that
and see how, in this case,the robots would behave.
Obviously, the challenge here
is to model the simulation test bed
as accurately as possible
so that we can depictall the possible things
that might go wrong in the real world.
And to be honest, we'll never get there,
we'll never get to 100%
(22:24):
of the true complexity of a warehouse.
But we wanna get to, let'ssay a confidence level
where we're like, okay,
we are sure enough about this algorithm,
now, we can actually testit in the real world.
Now, we can actually deploy this
to a pilot warehouse of somecustomer and see what happens.
And obviously, we wanna start small there,
test it out at a small scale
(22:44):
so that if something doesn'tbehave the way it should,
we can immediately interveneand the damage is limited.
But that's typically how this goes.
You first virtually test it,
then you do a smallscale real world pilot,
and then hopefully, everything pans out
and you can roll it out at scale.
- And I don't think I'm late to the game
in saying this theme ofthe importance of trust
when it comes to AI isgonna be just a growing
(23:06):
and growing theme.
And probably, it is already in academia,
but like I know that ourcolleague, Bryan Reamer,
with the Advanced VehicleTechnology Consortium
has been talking about,
like this is the only way
that we're gonna get movement on this,
when there is public trust.
But it seems like there is some level
of corporate trust here on Mecalux's side
for when you're putting forth that,
and high expectations
for when the IntelligentLogistics Assistance Lab
(23:28):
is producing some research.
So I guess for all of you, giventhat the trust exists there
or that you're trying to establish this,
how do you envision thispartnership between CTL
and the lab and Mecaluxinfluencing the future landscape
of supply chain management,of warehouse management,
things like that?
- So ultimately, our missionis to help, as I said before,
(23:48):
companies to achieveoperational excellence.
Whether it's AI, robotics,
or smart warehouse management systems,
or even distributedorder management systems,
we're constantly looking fornew ways to help our clients
to optimize their operations
and therefore be able tobetter utilize their resources
and save time and cost,
(24:09):
which is in the end, themain goal of every company.
So by this collaboration with MIT,
what we wanna do is that wewant to push the boundaries
of what's possible inthe logistics technology.
And we envision thatthis partnership leading
to breakthroughs in areaslike AI-driven automation,
predictive analytics, andsmart inter-logistics robots,
(24:31):
which we can then integrateinto our solutions
to help in the end, companies to operate
with a whole new level ofefficiency and productivity.
- We strongly believe thatthis research partnership
with MIT and with Matthias' team
will bring in the best andmost advanced technologies
to help managers make logisticsprocesses more efficient.
(24:53):
For example, with AI-enabled systems,
we can empower clientsto anticipate issues
before they arise.
They will be able tooptimize resource allocation
in real time and and makefaster data-driven decisions.
- If I may add to this.- Please.
- So obviously, you might ask,
well, we have, to some extent at least,
self-driving cars out there on the road.
(25:14):
We have companies that fly rockets
to space using machinelearning and AI to some extent,
I would assume.
So why does the logisticsindustry still not know
how to operate robots intelligently?
And I think the answer to that
is that the logisticsand supply chain industry
is notoriously risk averse,
(25:35):
which kind of relates towhat we discussed earlier
about that trust issue.
And also supply chainlogistics traditionally
has been very much focused on cost,
on very short term returns on investments.
And that's honestly oneof the main challenges
that we were facing in recent years
when we were looking for partners
(25:56):
to actually help us getthis type of research
off the ground.
Because it's not like the industry
didn't see the potentialvalue of these methods,
but the fact that it mighttake a couple of years
until we actually seesolutions emerge from this
that really turn the needlein terms of cost efficiency
or whatever the metric might be.
(26:17):
And the fact that we'retalking about methods
that may, at leastinitially, behave differently
from what we were expectingthem to behave like,
that usually turned a lotof traditional logistics,
supply chain management companies away
or basically made them not interested
in investing into researchand development in this space.
(26:38):
And that's why for us, it's such a fortune
that with Mecalux we found a partner
who was willing to takethat leap of faith,
both in terms of trusting the solution
and in terms of allowing us to experiment,
allowing us to build the foundations
without an immediate need
for a positive return on that investment.
(27:01):
- Well, let's talk a littlebit about that investment
or those expectations, I guess,which is, my understanding
is that this is an initialfive-year partnership
between CTL and the lab and Mecalux.
What are the hopes for the benchmarks
that you will see over those five years?
I don't know how concreteor ethereal they are.
Is it after year one,we're going to have X,
after year two, we're gonnahave Y, that kind of thing?
- I mean that's hard to predict.
(27:22):
Honestly, my main hopefor this is, first of all,
that this research collaboration
will be a little bit of a trailblazer,
if that's the right Englishword to use, I don't know, but-
- Makes sense to me. (giggles)
I've spoken English all my life.
- By the means given to usthrough this partnership,
we can show that AI and machine learning
is not just a buzzword,a little bit of sprinkle,
and at the end of theday, it's overly hyped,
(27:45):
but that we can actuallycome up with solutions
that are trustworthyand make economic sense,
make practical sense, make also sense
from an environmental,social point of view.
So basically make sense alongall the possible dimensions
along which we want
to optimize the futurelogistics systems out there.
And once we can show this,
(28:05):
we hope that this resistancethat I was describing earlier
of the logistics and supplychain industry as a whole
towards this type ofinnovation will slowly reduce
and we'll see more and more engagement
from a larger part of theindustry in academic research
that might hopefully bringthe logistics industry
back on track comparedto other industries.
(28:27):
And the other thing that very practically
that I hope to see from this partnership
is that we get to try outthings in the real world.
Because very often in academia,
you are a little bit in a weird situation
where you come up with super cool methods,
super powerful models,
you think you invented thebest thing since sliced bread,
(28:47):
and then no one is willingto actually try it out
in real life.
And here this partnership,I think we are at a point
where we want to try thisout in the real world.
And that's, for me, I wouldbe very happy if let's say,
in a year from now, wewould see some robots moving
around the warehousethat are actually powered
by some of the work that we do here.
(29:08):
- I'm sure we will.
- Yeah, I guess for Mecalux's guess,
like how do you see therole of what's happening,
not just here, but herein terms of the research
on the logistics side of thingsover the next five years,
but the other things thatMecalux is investing in.
Like how do you see theadvent of new technologies
being part of what you'redoing over the next few years?
- So over the next 5 to 10 years,
(29:29):
we see logistics continuing to transform
from a traditional support function
into a strategic driverof business growth.
Technologies like AI, machine learning,
productive analytics willplay a huge role on this.
They will enable moreprecise demand forecasting,
optimize inventory management,
and actually smarter decision-making
(29:52):
across the supply chain.
- And adding something towhat Iñaki has already said,
so we also foresee strongtrends in the market
towards greater automationand robots in warehouses.
So automation will nolonger be just an option
for large scale operations,
especially when we're talking
about smart inter-logisticsrobots like the AMRs.
(30:14):
So this is a really good way for companies
to make their first step with automation,
probably with affordable investments.
So it's gonna become more accessible
and essential for businesses of all sizes.
And what we've seen with labor shortages
and the need of faster turnaround times,
(30:34):
automation and digitization
and also the applicationof AI in all of this
will for sure play a key role
and it's gonna be really, really important
to meet customer expectationsin terms of speed,
accuracy, and flexibility.
(bright music)
- Thank you, this hasbeen the 31st episode
(30:54):
of "Supply Chain Frontiers."
We appreciate you joining us.
We appreciate the insights shared today
by Dr. Matthias Winkenbach of MIT CTL,
and our guests, Alejandro González
and Iñaki Fernández from Mecalux.
As we continue to explore
the intersection oftechnology in logistics,
it's clear that partnerships like these
are paving the way for a smarter
and more efficient supply chain landscape.
(31:15):
(bright music)
I'm not only fortunate enough
to host "Supply Chain Frontiers,"
but on this episode, I'mthe producer as well.
Our sound editor is DaveLashinsky of David Benjamin Sound.
Our audio engineer today
is Kurt Schneider of MITAudio Visual Services.
MIT "Supply Chain Frontiers"is recorded on the MIT campus
in Cambridge, Massachusetts.
Be sure to check out ourprevious episode with Matthias
(31:35):
for more context on this partnership.
And stay tuned for our nextepisode where we'll continue
to delve into the innovationsshaping the future
of supply chain management.
You can hear all episodesat ctl.mit.edu/podcasts
or search "Supply Chain Frontiers"
on your preferred pod host.
Until next time, onbehalf of the researchers,
instructors, staff and partners
here at the MIT Center forTransportation and Logistics,
(31:58):
I'm Benjy Kantor andthank you for listening.
(bright music)
Popular Podcasts
Amy Robach & T.J. Holmes present: Aubrey O’Day, Covering the Diddy Trial
Introducing… Aubrey O’Day Diddy’s former protege, television personality, platinum selling music artist, Danity Kane alum Aubrey O’Day joins veteran journalists Amy Robach and TJ Holmes to provide a unique perspective on the trial that has captivated the attention of the nation. Join them throughout the trial as they discuss, debate, and dissect every detail, every aspect of the proceedings. Aubrey will offer her opinions and expertise, as only she is qualified to do given her first-hand knowledge. From her days on Making the Band, as she emerged as the breakout star, the truth of the situation would be the opposite of the glitz and glamour. Listen throughout every minute of the trial, for this exclusive coverage. Amy Robach and TJ Holmes present Aubrey O’Day, Covering the Diddy Trial, an iHeartRadio podcast.
Betrayal: Season 4
Karoline Borega married a man of honor – a respected Colorado Springs Police officer. She knew there would be sacrifices to accommodate her husband’s career. But she had no idea that he was using his badge to fool everyone. This season, we expose a man who swore two sacred oaths—one to his badge, one to his bride—and broke them both. We follow Karoline as she questions everything she thought she knew about her partner of over 20 years. And make sure to check out Seasons 1-3 of Betrayal, along with Betrayal Weekly Season 1.
Crime Junkie
Does hearing about a true crime case always leave you scouring the internet for the truth behind the story? Dive into your next mystery with Crime Junkie. Every Monday, join your host Ashley Flowers as she unravels all the details of infamous and underreported true crime cases with her best friend Brit Prawat. From cold cases to missing persons and heroes in our community who seek justice, Crime Junkie is your destination for theories and stories you won’t hear anywhere else. Whether you're a seasoned true crime enthusiast or new to the genre, you'll find yourself on the edge of your seat awaiting a new episode every Monday. If you can never get enough true crime... Congratulations, you’ve found your people. Follow to join a community of Crime Junkies! Crime Junkie is presented by audiochuck Media Company.