August 31, 2022 • 24 mins
In this episode of "Let's Talk Farm to Fork", we're joined by Charlie Andersen, from Burro, who we will be talking to about how their autonomous robots are helping optimise field labour for fresh supplies through carrying, towing, scouting, and beyond.
https://burro.ai/
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Voiceover (00:02):
Welcome to let's talk farm to fork, the PostHarvest
podcast that interviews people,making an impact in the fresh
produce sector.
We'll take a deep dive into whatthey do and find out how they're
helping to reduce the amount offood lost or wasted along the
farm to fork journey.
But before we get started, didyou know that according to the
(00:23):
UN's food and agricultureorganisation, around 45% of the
world's fruits and vegetables goto waste each year?
If you would like to learn moreabout how you can practically
play your part in maximisingfruit and vegetable supplies,
whether you're a part of theindustry or simply a consumer
visit PostHarvest.Com and tryout their free online course
(00:45):
library today.
Now time for your host MitchellDenton.
Mitchell Denton (00:50):
Hi there, and welcome to"Let's Talk Farm to
Fork", the PostHarvest podcastthat interviews people of
interest across the food supplychain.
Today on our show, I'm joined byCharlie Andersen, from Burro.
Who I'll be talking to about howtheir autonomous robots are
helping optimise field labourfor fresh supplies through
carrying, towing, scouting andbeyond.
So with no further delays let'sget started.
(01:14):
Well, hello, Charlie.
How are you?
Thanks for joining me on thepodcast today.
Charlie Andersen (01:18):
Yeah Mitch, great.
Great to be here.
Really appreciate the interestand, and, uh, great to be here.
Mitchell Denton (01:22):
Of course, of course.
Before we get into it, I justwanted to give you the
opportunity to tell us a littlebit about yourself, and what you
do, and maybe just a fun factabout yourself.
Charlie Andersen (01:32):
Yeah, sure thing.
So, uh, so my name is, CharlieAnderson, um, I grew up on a, I
guess, a working fruit andvegetable farm in Pennsylvania
on the east coast of the US.
And my, I guess my, my kind oflifelong obsession has been
trying to figure out ways withinfarming of doing work from a
tractor cab and not having toget out of the tractor cab to go
(01:53):
to work by hand.
Um, and that interest has led meto where I am today.
Today I run a company calledBurro.
Uh, we build, you caneffectively think of it as, as
Disney's"Wall-E for agriculture"in a 1.0 format.
So a computer vision-based,autonomous ground vehicle.
That does a variety of tasksoutdoors and is designed to lay
(02:14):
the base for a lot more autonomyover time.
Um, and in terms of fun fact, Iguess, as I thinking through
things, I, I, on my family farm,I built a road that is now
mapped on Google Earth.
So that's one, one fun fact, ifyou will.
Mitchell Denton (02:28):
Which road is that?
If you don't mind me asking.
Charlie Andersen (02:31):
It's a, um, it's a gravel road that goes
about like three quarters of amile up a hill.
Uh, and, um, did it with a, witha, basically a small bulldozer.
Mitchell Denton (02:43):
Yeah.
Wow.
Charlie Andersen (02:43):
So, uh, so not yet, not one that you could
just, you know, randomly get on,get into a car and go on, but,
but still sits on Google Earth,which is somewhat of a bragging
right for me, if you will.
Mitchell Denton (02:51):
Yeah, that's pretty cool.
All right, well, before we getbogged down in road talk, let's
talk fun to fork.
So, continuing on from youtelling us what you do.
I really enjoyed that Wall-Edefinition that you gave of your
technology, would you mindtelling us a little bit more
about the history behind Burroand how your innovative
technology works?
Charlie Andersen (03:12):
Yeah, sure thing.
So again, grew up on a workingfarm.
I got an MBA and got out ofbusiness school, went to go work
for CNH, which is Deere'slargest competitor.
And there part of my role wasselling and marketing machinery
to farmers.
And the other portion, uh, Ispent a fair amount of time
looking at autonomy companiesfrom an acquisition perspective
(03:33):
for the company.
And from like a really, reallykind of frustrated with how
slowly robotics was making itsway into agriculture and kind of
how almost how uninterest largeincumbents like some of the ones
I was working for, um, were,were moving.
And so I had a, I believe I hada colleague whose family had a
chicken farm, and idea numberone became,"Hey, I'm gonna go
(03:53):
figure out how to build a robotto pick up dead chickens.
And, and needless to say thatwe, we've pivoted from that
concept...
Mitchell Denton (04:00):
Yeah.
Charlie Andersen (04:01):
Quite a bit.
But as I was looking at thatidea, what I was discovering was
that there are all sorts ofapplications within agriculture.
Where you have people movingthrough the world, perceiving
stuff around them, and thenmanipulating things.
And if you can do the mobilitypart and possibly the perception
part that platform can get intoa ton of different use cases.
(04:24):
And, and that kind of led me to,again, what our product is
today, which is an autonomousground vehicle used in primarily
in vineyards, nurseries andberry operations, but get kinda
getting pulled into a bunch ofother sectors.
Mitchell Denton (04:38):
Hmm.
Yeah, no, that's great.
So what would you say separatesBurro technology from other
labour solutions currently onthe market?
Charlie Andersen (04:47):
Yeah, totally.
So, there's this thing withinrobotics called"Moravec's
paradox", it's, it's the notionthat it's a lot easier to make a
computer that can play chess,than it is to make a computer or
a robot drive across the room.
And so said another way, ifyou're a robot on a farm, you
have to one understand where areyou in the world?
(05:08):
You have to then understand howto move from A to B, what's
around you, and then ultimately,how do you manipulate those
things around you?
And I think the way a lot ofcompanies have tried to tackle
autonomy on farm to date haslargely been by automating a
tractor or by trying to go outand pick fruit.
(05:29):
And if you look at othersegments such as warehousing or
factories, the way robots haveinitially started has been by
picking a very constrained typeof mobility and beginning with
that mobility.
But later over time doing morethings.
And so, what we have done iswe've built what's basically a
(05:49):
four or five horsepowerautonomous farm ATV.
That can carry around 400 to 500pounds around 225 or 230
kilograms.
And what that vehicle does is itcan be operated by any person on
a farm.
It can run without any sort ofcentral control system.
(06:12):
And it uses a combination ofcomputer vision and high
persistent GPS, plus a ton of,uh, artificial intelligence to
follow people and structurewithin an environment to learn
roots and effectively to carryor tow heavy things from A to B
to C and to perceive thingsaround it or to scout things
(06:32):
around it.
And so you, you might ask, sowhat's the use case for a
product that moves from A to Bto C alongside people within
agriculture?
I think what, what we have foundis that, within ag, there are
all sorts of settings whereyou've got people working under
canopies, so you can't just useGPS to navigate.
And you've got people that arecarrying heavy things around and
(06:53):
the people that do a lot oflabour on farm, tend not to be
equipment operators.
They tend to be, you know,relatively, um, uh, less
sophisticated from a machineryperspective.
And so what separates our systemfrom pretty much everything else
on the market.
Is that its operating undercanopies and out in the open.
So with GPS and without GPS andit's working safely alongside
(07:16):
people to carry heavy things.
And that's, so we're, kind of aweird duck in the marketplace
where not many other companieshave something like ours and we
actually can't quite figure outwhy that is the case, we're just
a weird company in a way.
Mitchell Denton (07:27):
Yeah, no, that's cool.
I, I, I really love the marriageof complexity and simplicity
with the technology it's such a,um, a straightforward
application, obviously there'sa, there's a whole lot of
backend work that goes into thatsimplicity, but it's just a
really cool, uh, solution at theend of the day, it's really
cool.
So, Agriculture and AgTech seemsto be a market that is currently
(07:50):
garnering the attention of bigVC firms these days.
In fact, I see that ToyotaVentures has recently
contributed to funding to Burro.
Are VC's attracted to AgTechbecause of its frontier
technology aspect or morebecause of its sustainable
outcomes?
Charlie Andersen (08:07):
Yeah.
So I'm trying to think of howto, so how to answer that.
So there, there are pros andcons of agriculture.
So when you think about, whenyou think about Ag,
specifically, half of revenuetends to be crops and half of
revenue tends to be livestock.
Within crops, you've got grains,so corn, wheat, soybeans, and
those at least within the US aresomething like 70% of farm
(08:29):
revenue.
But only about 8 to 10% of farmlabour.
And then you've got all thespecialty crops and those are
roughly 30% of farm revenue, but80 to 90% of farm labour.
And that, that disparity has fora long period of time, really
scared people away frominvesting in Ag because where
(08:50):
all the labour is, tends to bein these kind of nichey, funky
different use cases that arereally difficult to automate
comprehensively.
And if you automate one use casecomprehensively, ie pick
strawberries, then you're onlyable to pick strawberries and
only in one production style andcan't move to nursery crops or,
or cherry tomatoes or somethingelse.
(09:12):
Um, so that's kind of the,that's the kind of why have a
lot of investors shied away fromit historically from a TAM
perspective?
The other reason that peoplehave shied away from it has been
that it's really, reallydifficult to do.
So I think it's, it's remarkablyeasy to prototype something that
works in a demo or kind of avideo type context.
But as you go from 1 to 50, to100 to 200 systems running your
(09:38):
system has to handle a ton ofadditional variability.
And that variability increasesalmost exponentially for each
additional unit you haverunning, which means it's very
difficult to build somethingthat's reliable, and can do what
people actually expect.
So those are the kind of, whynot thus far, small nichey,
funky TAMS, and then really,really difficult to get the
technology working.
The flip side of it is that thedifficulty also exists on road
(10:01):
or in a lot of these othersegments and Ag, you can move
slowly, you're off road, youtend to be away from tons and
tons of people, or at least thepublic.
And there's a huge labourdynamic that is begging to be
tackled.
And the second thing, so, so notonly is there a really
pervasive, specific need.
(10:22):
I think the second thing is thatthe need can be met increasingly
by computer vision basedautonomy.
And so from all of this, nobodyhas succeeded yet.
There's all of this potentialdemand that people can kind of
see.
And, and the technology issuddenly there.
And so I think some of thecompanies that operate today,
(10:44):
ours hopefully including, willbe really, really significant
companies ultimately, but itkind of has a feeling of like,
"Mount Everest in 1948" or like"PCs in 1976", you know, it's
early stage, early days.
Nobody has succeeded yet, butyou can kind of sense that
there's something on thehorizon.
I think that, that's what Toyotaand F-Prime and Cibus and, and
(11:07):
some of our investors amongstmany others are starting to
really, to really see.
Mitchell Denton (11:10):
Mm.
Yeah, so then what would you sayis the biggest challenge your
team has encountered so far withyour innovative robots and how
did you overcome it?
Charlie Andersen (11:19):
Um, localisation is the hardest
problem that we've encounteredbar none.
And it's, it's something that'sobvious, it's everywhere, and
it's so obvious that peopledon't even see it.
But it's how do you answer thequestion of where are you in the
world when you're going out inthe open and under canopies, and
that if you can't reliablyanswer, where are you in the
(11:42):
world?
It's very difficult to build asystem that can behave really
reliably.
Um, and just to, to unpack thata bit more, you, you have, even
fairly simple things that seemsimple to your reptilian brain,
uh, that are incrediblydifficult to do for a robot.
If you're living from A, to B toC in an outdoor setting, and you
go from out in the open to undera canopy, you go from having
(12:03):
perfect GPS to no GPS or GPSthat is bouncing around like a,
marble in a blender with the topoff.
So you're, you've got one signalin your system that's bouncing
around all over the place, andthen you're going from bright
light to dark light.
And you tend to be doing it inenvironments where tons of stuff
is moving around.
Uh, so lighting is changing allday long, shadows are moving
around, things are movingaround, et cetera.
(12:25):
And so I think for us, theobvious thing is that
localisation is really, reallydifficult to do well.
And from that, our assumption isthat if we can do it really,
really well, then our system canbecome a platform for others to
use.
And separately from that, it's aland of no silver bullets, only
lead ones.
There's no like, one singlesolution that solves at all.
(12:48):
It's, it's you have to run 30,50, 100 thousand plus miles or,
or, you know, a million plusmiles with systems and real
world conditions and encounteredge cases constantly, and just
kind of gradually hammer awaywith different solutions to all
the kind nichey specificproblems that come up.
So yeah, so that's a very longwind explanation, but
(13:08):
localisation is really hard,difficult to do well, and in
terms of how we haveaccomplished it or overcome it
thus far, we have not overcomeit in every single use case thus
far yet.
Our systems function between 15and 20 autonomous miles per user
intervention today.
And at those types of rates,roughly 30% of our faults relate
(13:32):
to robots being lost.
When they're lost, they stop.
So the problem is largelymitigated.
And what we discover is that aswe go into new environments, the
way you solve the localisationproblem changes somewhat.
Although the same stack canultimately build work across
everything.
Mitchell Denton (13:52):
Yeah wow.
I mean, continuing on thisthread of biggest challenges.
While working in AgTech, whathave you found to be the biggest
surprise?
Charlie Andersen (14:00):
You know, to me, it's just all about the
people.
I think it's kind of the, the,the, this is ultimately,
technology and technology withinAgTech is a pure people
business.
You need an incredible team tobuild a product.
That team needs to be really,intrinsically motivated because
no single person has all theanswers of how to solve those
problems.
(14:21):
And then you need to buildproduct that end users love and
can figure out how to operate.
And I, you know, as somebody whoshould be considered classically
trained in this domain, I grewup on a working farm.
I, I worked for a big Agequipment company.
It's definitely been a surpriseto me, how much of a people
business I'm in, uh, and, andlargely when we have, we have
(14:44):
problems or opportunities, mostof them centre around finding
great people, getting themreally, really motivated and
really satisfying an end userwith what the product does.
Mitchell Denton (14:53):
Yeah, absolutely.
I, I would take it a stepfurther and say even beyond like
the inner team, just the groupsof people within the industry
that are more than happy tocollaborate and really want to
see success just across theboard.
Charlie Andersen (15:06):
Totally, and it's, I think it's, it's also
surprisingly small.
Like you run into these events.
You have somebody that that'sfamiliar because you've seen
them on a website somewhere.
Like it, it, it, I think itvery, very quickly builds.
Like I, four years ago, I'd flyout to California, like sleep in
the trunk of a KIA and go meetwith people.
And a lot of the people I, I metfrom four years ago have just
kind of like spiraled into amillion other connections.
And typically like the second orthird person I meet in the space
(15:31):
leads me back to somebody I metpreviously.
I think it's a really, it's justa, a really cool industry from
that perspective with tonsenthusiastic, bright, driven
people that, that really lovewhat, they do.
Mitchell Denton (15:40):
Yeah, totally.
Totally.
So, from your perspective, whatdo you identify as being one of
the biggest pain points or blindspots in the food industry?
Charlie Andersen (15:49):
I'm not sure if it's a, if it's a blind spot
more just of a pain point, Ithink that within our space,
people talk about labour being apain point.
And I think that, that labour isa real pain point, but it has a
bunch of layers to it.
I think that the real pain pointis that nobody wants to get up
(16:10):
anymore and go into a field at5:00 AM in the morning and work
from dawn to dusk in 110 degreeheat.
And the people that are stillwilling to do that work
increasingly, um, are demandingbetter conditions and also are
wanting to be kind of upskilledto be able to do more per unit
of time than they kind of do.
So again, I think, I thinklabour is a big pain point.
(16:32):
I think it's described typicallykind of in an abstract way and
you really need to think aboutlike,"Who's doing the work?" And
like, like I, I, I willencounter crews all the time
where like, you know, there'llbe a father, mother, son or
daughter team.
And like the parents are workingincredibly hard cause they want
their kids to be better.
And then they'll pull their kidsin the field to show their kids
how hard field work is toinspire their kids, to do
(16:55):
something else or to work harderin school or do something.
And so labour is a big painpoint and the blind spot in all
that is there are people workingon these farms, you really gotta
go talk with them to understand,basically to understand their
dynamics.
Mitchell Denton (17:05):
Absolutely.
So, when it comes to food lossand sustainable farming, what's
the biggest area your team arecurious about and why?
Charlie Andersen (17:15):
The English economist, Thomas Malthus, he
talks about how at some point,all, all populations reach the
point at which they're consumingall resources or they're over
consuming resources in theenvironment can no longer
sustain them.
And I think that in the case ofpeople, if you fast forward the
clock on where human populationis going, in the next couple of
years, or say the next 30 yearsor so, we are supposed to reach
(17:39):
the point where we are consumingthree X, what the planet
produced in 2010, which, whichobviously is not going to
happen.
And so to me, what I'm mostcurious about, I think, I think
in the past we've had themechanical revolution, we've had
a chemistry revolution, we'vehad a, a genetically modified
organisms revolution and allthose things.
(18:00):
And to me, what I'm most curiousabout is how big of a picture
can automation play in basicallydoing three X more in food
production than what we're doingtoday.
And, and if you, if you thinkabout like, what do you do in
your, what do you do in yourgarden?
When you see a beetle eating theleaf of a tomato plant, well you
squish it and you do that on aplant by plant basis, you're,
(18:21):
you're manipulating anindividual thing.
You get into big production Ag,you can't do that, you've gotta
do the same thing on everything.
I think that being able to seesomething and behave very
specifically to it in real timehas this huge potential to alter
the way we actually producefood.
And I'm very curious about howthat takes place.
(18:42):
And then the final question andall that is,"is all that, all
that done by one company?" And Idon't think it is.
I think it's actually done bymany, many different companies
and some will be buildingmobility, others are gonna be
building things around theneural networks to identify
particular diseases and there'dbe ones working on manipulation
and ones doing distribution.
Um, so yeah, there's a lengthylist of questions to what was
(19:02):
probably intended as a 30 secondanswer, so those are something
of the things that are tricklingthrough my mind.
Mitchell Denton (19:07):
No, this is the good stuff.
This is why I asked thequestions.
So continue on with thisthought.
Is there a particular group orinnovation within the industry
that you're excitedly keeping awatchful eye on?
Charlie Andersen (19:19):
So, going back to the layers comment, I think
there's a, there's a groupcalled Western Growers
Association.
And they have a perspective onautonomy that, that things are
ultimately gonna be built inlayers.
Um and, I really share thatperspective.
I think that that will also takeplace, um, at the same time,
with the way the industry istoday, a lot of the groups are
(19:42):
very reticent to work withothers, because it's unclear
who's a competitor and who's a,who's a, who's a friend, who's a
friend who's a fo is kind ofunclear.
Um, and so what I'm particularlyinterested in is following the
work that Western GrowersAssociation is doing to
encourage layers and then tryingto figure out what we can do as
a company to build the ultimatemobility platform on top of
(20:04):
which other companies mightbuild their manipulation system
or crop perception system, or...
I had a guy email me today witha, with a system that's supposed
to navigate around and feedanimals.
There are all of these funkyideas where I don't think that
one company does them all.
I think they're actually layers.
And I'm kind of curious how theindustry and how companies in
the industry can advance that.
Mitchell Denton (20:26):
Yeah.
Yeah.
So then what's one thing youwish you'd known when you began
your career in developingautonomous farming robots?
Charlie Andersen (20:35):
Um, I think it's just really hard and that's
that's, um, it's, it's hard.
People talk about barriers toentry and, and patent protection
and, and things like that.
And, and the realities ofbuilding these systems is so
incredibly hard.
I think that had I known thatfrom the outset, I probably
(20:57):
wouldn't have done what I'mdoing today and it probably
would be...
like, I I'm glad that I'm doingtoday what I'm doing today, but
that, but that said, I thinkit's really, really hard.
And I think just kind ofrecognition of what's the stuff
that is, it's not obvious fromthe outset, what is going to be
hard as you get into it.
Mitchell Denton (21:14):
Yeah.
Absolutely.
Absolutely.
So Charlie, we are unfortunatelycoming to a close, but as this
episode draws to a close, is themain point you want the
listeners to take away?
Charlie Andersen (21:26):
Yeah, so I think, people are kind of oddly
good at predicting where theworld is going in 10 to 20
years, but really, reallystruggle to predict how do you
win in years 1 through 5.
And to me, the main point, atleast as it, pertains to my
company in this topic.
Is that I think that in 10 to 20years, you're gonna see millions
(21:47):
of robots doing a variety oftasks on farm and elsewhere.
I think that the approach thatwe are taking, beginning with a
mobility platform, starting invineyards and nurseries and
berries is a unique approachthat appears to be proving
successful today.
And that if companies areseeking to build layers around
(22:10):
that require mobility, requireperception or, or require moving
manipulation from A to B, wewould love to partner with them.
And then I think that again, Ithink fast forward two decades
from today, and again, the sameway that you have a Roomba
navigating through your kitchen,vacuum cleaning.
I think you're gonna have tonsof small autonomous systems in
(22:33):
the world's largest industrydoing a whole host of different
tasks.
And so it's almost like we'resitting in, we're sitting in
1977 or 78 as early, early maintrains and PCs are emerging and
we're trying to envision Twitterand that's a really, really
exciting place to be.
But also we're very much kind ofpredicting something before it's
(22:55):
happens, which again, exciting.
Paving the way for a future,solving huge problems, but also
a, uh, an unpredictable place tobe in the world.
Mitchell Denton (23:02):
Absolutely.
I look forward to seeing whatlays ahead for the next few
years.
Charlie Andersen (23:06):
Yeah, me too.
Mitchell Denton (23:08):
Well, that's all for today's episode"Let's
Talk Farm to Fork".
Thanks for listening.
And thank you, Charlie, forjoining me today.
Charlie Andersen (23:14):
Great, Mitch.
Thank you so much, we reallyappreciate being on.
So thank you.
Mitchell Denton (23:17):
If you'd like to know more about Charlie and
Burro, check out the link andthe description on the episode,
make sure to subscribe to thepodcast so that you never miss
an episode.
And don't forget to leave areview and share with your
friends.
Until next time you've beenlistening to"Let's Talk Farm to
Fork", a PostHarvest podcast.
Voiceover (23:32):
We appreciate you joining us for this episode of
let's talk, farm to fork, besure to rate, review and
subscribe.
Also, if you would like to learnmore about how you can
practically play your part inmaximizing fruit and vegetable
supplies, whether you're asupplier, consumer, or anyone in
between the farm to forkjourney, visit PostHarvest.Com
(23:55):
and try out their free onlinecourse library today.
Welcome to let's talk farm to fork, the PostHarvest
podcast that interviews people,making an impact in the fresh
produce sector.
We'll take a deep dive into whatthey do and find out how they're
helping to reduce the amount offood lost or wasted along the
farm to fork journey.
But before we get started, didyou know that according to the
(00:23):
UN's food and agricultureorganisation, around 45% of the
world's fruits and vegetables goto waste each year?
If you would like to learn moreabout how you can practically
play your part in maximisingfruit and vegetable supplies,
whether you're a part of theindustry or simply a consumer
visit PostHarvest.Com and tryout their free online course
(00:45):
library today.
Now time for your host MitchellDenton.
Mitchell Denton (00:50):
Hi there, and welcome to"Let's Talk Farm to
Fork", the PostHarvest podcastthat interviews people of
interest across the food supplychain.
Today on our show, I'm joined byCharlie Andersen, from Burro.
Who I'll be talking to about howtheir autonomous robots are
helping optimise field labourfor fresh supplies through
carrying, towing, scouting andbeyond.
So with no further delays let'sget started.
(01:14):
Well, hello, Charlie.
How are you?
Thanks for joining me on thepodcast today.
Charlie Andersen (01:18):
Yeah Mitch, great.
Great to be here.
Really appreciate the interestand, and, uh, great to be here.
Mitchell Denton (01:22):
Of course, of course.
Before we get into it, I justwanted to give you the
opportunity to tell us a littlebit about yourself, and what you
do, and maybe just a fun factabout yourself.
Charlie Andersen (01:32):
Yeah, sure thing.
So, uh, so my name is, CharlieAnderson, um, I grew up on a, I
guess, a working fruit andvegetable farm in Pennsylvania
on the east coast of the US.
And my, I guess my, my kind oflifelong obsession has been
trying to figure out ways withinfarming of doing work from a
tractor cab and not having toget out of the tractor cab to go
(01:53):
to work by hand.
Um, and that interest has led meto where I am today.
Today I run a company calledBurro.
Uh, we build, you caneffectively think of it as, as
Disney's"Wall-E for agriculture"in a 1.0 format.
So a computer vision-based,autonomous ground vehicle.
That does a variety of tasksoutdoors and is designed to lay
(02:14):
the base for a lot more autonomyover time.
Um, and in terms of fun fact, Iguess, as I thinking through
things, I, I, on my family farm,I built a road that is now
mapped on Google Earth.
So that's one, one fun fact, ifyou will.
Mitchell Denton (02:28):
Which road is that?
If you don't mind me asking.
Charlie Andersen (02:31):
It's a, um, it's a gravel road that goes
about like three quarters of amile up a hill.
Uh, and, um, did it with a, witha, basically a small bulldozer.
Mitchell Denton (02:43):
Yeah.
Wow.
Charlie Andersen (02:43):
So, uh, so not yet, not one that you could
just, you know, randomly get on,get into a car and go on, but,
but still sits on Google Earth,which is somewhat of a bragging
right for me, if you will.
Mitchell Denton (02:51):
Yeah, that's pretty cool.
All right, well, before we getbogged down in road talk, let's
talk fun to fork.
So, continuing on from youtelling us what you do.
I really enjoyed that Wall-Edefinition that you gave of your
technology, would you mindtelling us a little bit more
about the history behind Burroand how your innovative
technology works?
Charlie Andersen (03:12):
Yeah, sure thing.
So again, grew up on a workingfarm.
I got an MBA and got out ofbusiness school, went to go work
for CNH, which is Deere'slargest competitor.
And there part of my role wasselling and marketing machinery
to farmers.
And the other portion, uh, Ispent a fair amount of time
looking at autonomy companiesfrom an acquisition perspective
(03:33):
for the company.
And from like a really, reallykind of frustrated with how
slowly robotics was making itsway into agriculture and kind of
how almost how uninterest largeincumbents like some of the ones
I was working for, um, were,were moving.
And so I had a, I believe I hada colleague whose family had a
chicken farm, and idea numberone became,"Hey, I'm gonna go
(03:53):
figure out how to build a robotto pick up dead chickens.
And, and needless to say thatwe, we've pivoted from that
concept...
Mitchell Denton (04:00):
Yeah.
Charlie Andersen (04:01):
Quite a bit.
But as I was looking at thatidea, what I was discovering was
that there are all sorts ofapplications within agriculture.
Where you have people movingthrough the world, perceiving
stuff around them, and thenmanipulating things.
And if you can do the mobilitypart and possibly the perception
part that platform can get intoa ton of different use cases.
(04:24):
And, and that kind of led me to,again, what our product is
today, which is an autonomousground vehicle used in primarily
in vineyards, nurseries andberry operations, but get kinda
getting pulled into a bunch ofother sectors.
Mitchell Denton (04:38):
Hmm.
Yeah, no, that's great.
So what would you say separatesBurro technology from other
labour solutions currently onthe market?
Charlie Andersen (04:47):
Yeah, totally.
So, there's this thing withinrobotics called"Moravec's
paradox", it's, it's the notionthat it's a lot easier to make a
computer that can play chess,than it is to make a computer or
a robot drive across the room.
And so said another way, ifyou're a robot on a farm, you
have to one understand where areyou in the world?
(05:08):
You have to then understand howto move from A to B, what's
around you, and then ultimately,how do you manipulate those
things around you?
And I think the way a lot ofcompanies have tried to tackle
autonomy on farm to date haslargely been by automating a
tractor or by trying to go outand pick fruit.
(05:29):
And if you look at othersegments such as warehousing or
factories, the way robots haveinitially started has been by
picking a very constrained typeof mobility and beginning with
that mobility.
But later over time doing morethings.
And so, what we have done iswe've built what's basically a
(05:49):
four or five horsepowerautonomous farm ATV.
That can carry around 400 to 500pounds around 225 or 230
kilograms.
And what that vehicle does is itcan be operated by any person on
a farm.
It can run without any sort ofcentral control system.
(06:12):
And it uses a combination ofcomputer vision and high
persistent GPS, plus a ton of,uh, artificial intelligence to
follow people and structurewithin an environment to learn
roots and effectively to carryor tow heavy things from A to B
to C and to perceive thingsaround it or to scout things
(06:32):
around it.
And so you, you might ask, sowhat's the use case for a
product that moves from A to Bto C alongside people within
agriculture?
I think what, what we have foundis that, within ag, there are
all sorts of settings whereyou've got people working under
canopies, so you can't just useGPS to navigate.
And you've got people that arecarrying heavy things around and
(06:53):
the people that do a lot oflabour on farm, tend not to be
equipment operators.
They tend to be, you know,relatively, um, uh, less
sophisticated from a machineryperspective.
And so what separates our systemfrom pretty much everything else
on the market.
Is that its operating undercanopies and out in the open.
So with GPS and without GPS andit's working safely alongside
(07:16):
people to carry heavy things.
And that's, so we're, kind of aweird duck in the marketplace
where not many other companieshave something like ours and we
actually can't quite figure outwhy that is the case, we're just
a weird company in a way.
Mitchell Denton (07:27):
Yeah, no, that's cool.
I, I, I really love the marriageof complexity and simplicity
with the technology it's such a,um, a straightforward
application, obviously there'sa, there's a whole lot of
backend work that goes into thatsimplicity, but it's just a
really cool, uh, solution at theend of the day, it's really
cool.
So, Agriculture and AgTech seemsto be a market that is currently
(07:50):
garnering the attention of bigVC firms these days.
In fact, I see that ToyotaVentures has recently
contributed to funding to Burro.
Are VC's attracted to AgTechbecause of its frontier
technology aspect or morebecause of its sustainable
outcomes?
Charlie Andersen (08:07):
Yeah.
So I'm trying to think of howto, so how to answer that.
So there, there are pros andcons of agriculture.
So when you think about, whenyou think about Ag,
specifically, half of revenuetends to be crops and half of
revenue tends to be livestock.
Within crops, you've got grains,so corn, wheat, soybeans, and
those at least within the US aresomething like 70% of farm
(08:29):
revenue.
But only about 8 to 10% of farmlabour.
And then you've got all thespecialty crops and those are
roughly 30% of farm revenue, but80 to 90% of farm labour.
And that, that disparity has fora long period of time, really
scared people away frominvesting in Ag because where
(08:50):
all the labour is, tends to bein these kind of nichey, funky
different use cases that arereally difficult to automate
comprehensively.
And if you automate one use casecomprehensively, ie pick
strawberries, then you're onlyable to pick strawberries and
only in one production style andcan't move to nursery crops or,
or cherry tomatoes or somethingelse.
(09:12):
Um, so that's kind of the,that's the kind of why have a
lot of investors shied away fromit historically from a TAM
perspective?
The other reason that peoplehave shied away from it has been
that it's really, reallydifficult to do.
So I think it's, it's remarkablyeasy to prototype something that
works in a demo or kind of avideo type context.
But as you go from 1 to 50, to100 to 200 systems running your
(09:38):
system has to handle a ton ofadditional variability.
And that variability increasesalmost exponentially for each
additional unit you haverunning, which means it's very
difficult to build somethingthat's reliable, and can do what
people actually expect.
So those are the kind of, whynot thus far, small nichey,
funky TAMS, and then really,really difficult to get the
technology working.
The flip side of it is that thedifficulty also exists on road
(10:01):
or in a lot of these othersegments and Ag, you can move
slowly, you're off road, youtend to be away from tons and
tons of people, or at least thepublic.
And there's a huge labourdynamic that is begging to be
tackled.
And the second thing, so, so notonly is there a really
pervasive, specific need.
(10:22):
I think the second thing is thatthe need can be met increasingly
by computer vision basedautonomy.
And so from all of this, nobodyhas succeeded yet.
There's all of this potentialdemand that people can kind of
see.
And, and the technology issuddenly there.
And so I think some of thecompanies that operate today,
(10:44):
ours hopefully including, willbe really, really significant
companies ultimately, but itkind of has a feeling of like,
"Mount Everest in 1948" or like"PCs in 1976", you know, it's
early stage, early days.
Nobody has succeeded yet, butyou can kind of sense that
there's something on thehorizon.
I think that, that's what Toyotaand F-Prime and Cibus and, and
(11:07):
some of our investors amongstmany others are starting to
really, to really see.
Mitchell Denton (11:10):
Mm.
Yeah, so then what would you sayis the biggest challenge your
team has encountered so far withyour innovative robots and how
did you overcome it?
Charlie Andersen (11:19):
Um, localisation is the hardest
problem that we've encounteredbar none.
And it's, it's something that'sobvious, it's everywhere, and
it's so obvious that peopledon't even see it.
But it's how do you answer thequestion of where are you in the
world when you're going out inthe open and under canopies, and
that if you can't reliablyanswer, where are you in the
(11:42):
world?
It's very difficult to build asystem that can behave really
reliably.
Um, and just to, to unpack thata bit more, you, you have, even
fairly simple things that seemsimple to your reptilian brain,
uh, that are incrediblydifficult to do for a robot.
If you're living from A, to B toC in an outdoor setting, and you
go from out in the open to undera canopy, you go from having
(12:03):
perfect GPS to no GPS or GPSthat is bouncing around like a,
marble in a blender with the topoff.
So you're, you've got one signalin your system that's bouncing
around all over the place, andthen you're going from bright
light to dark light.
And you tend to be doing it inenvironments where tons of stuff
is moving around.
Uh, so lighting is changing allday long, shadows are moving
around, things are movingaround, et cetera.
(12:25):
And so I think for us, theobvious thing is that
localisation is really, reallydifficult to do well.
And from that, our assumption isthat if we can do it really,
really well, then our system canbecome a platform for others to
use.
And separately from that, it's aland of no silver bullets, only
lead ones.
There's no like, one singlesolution that solves at all.
(12:48):
It's, it's you have to run 30,50, 100 thousand plus miles or,
or, you know, a million plusmiles with systems and real
world conditions and encounteredge cases constantly, and just
kind of gradually hammer awaywith different solutions to all
the kind nichey specificproblems that come up.
So yeah, so that's a very longwind explanation, but
(13:08):
localisation is really hard,difficult to do well, and in
terms of how we haveaccomplished it or overcome it
thus far, we have not overcomeit in every single use case thus
far yet.
Our systems function between 15and 20 autonomous miles per user
intervention today.
And at those types of rates,roughly 30% of our faults relate
(13:32):
to robots being lost.
When they're lost, they stop.
So the problem is largelymitigated.
And what we discover is that aswe go into new environments, the
way you solve the localisationproblem changes somewhat.
Although the same stack canultimately build work across
everything.
Mitchell Denton (13:52):
Yeah wow.
I mean, continuing on thisthread of biggest challenges.
While working in AgTech, whathave you found to be the biggest
surprise?
Charlie Andersen (14:00):
You know, to me, it's just all about the
people.
I think it's kind of the, the,the, this is ultimately,
technology and technology withinAgTech is a pure people
business.
You need an incredible team tobuild a product.
That team needs to be really,intrinsically motivated because
no single person has all theanswers of how to solve those
problems.
(14:21):
And then you need to buildproduct that end users love and
can figure out how to operate.
And I, you know, as somebody whoshould be considered classically
trained in this domain, I grewup on a working farm.
I, I worked for a big Agequipment company.
It's definitely been a surpriseto me, how much of a people
business I'm in, uh, and, andlargely when we have, we have
(14:44):
problems or opportunities, mostof them centre around finding
great people, getting themreally, really motivated and
really satisfying an end userwith what the product does.
Mitchell Denton (14:53):
Yeah, absolutely.
I, I would take it a stepfurther and say even beyond like
the inner team, just the groupsof people within the industry
that are more than happy tocollaborate and really want to
see success just across theboard.
Charlie Andersen (15:06):
Totally, and it's, I think it's, it's also
surprisingly small.
Like you run into these events.
You have somebody that that'sfamiliar because you've seen
them on a website somewhere.
Like it, it, it, I think itvery, very quickly builds.
Like I, four years ago, I'd flyout to California, like sleep in
the trunk of a KIA and go meetwith people.
And a lot of the people I, I metfrom four years ago have just
kind of like spiraled into amillion other connections.
And typically like the second orthird person I meet in the space
(15:31):
leads me back to somebody I metpreviously.
I think it's a really, it's justa, a really cool industry from
that perspective with tonsenthusiastic, bright, driven
people that, that really lovewhat, they do.
Mitchell Denton (15:40):
Yeah, totally.
Totally.
So, from your perspective, whatdo you identify as being one of
the biggest pain points or blindspots in the food industry?
Charlie Andersen (15:49):
I'm not sure if it's a, if it's a blind spot
more just of a pain point, Ithink that within our space,
people talk about labour being apain point.
And I think that, that labour isa real pain point, but it has a
bunch of layers to it.
I think that the real pain pointis that nobody wants to get up
(16:10):
anymore and go into a field at5:00 AM in the morning and work
from dawn to dusk in 110 degreeheat.
And the people that are stillwilling to do that work
increasingly, um, are demandingbetter conditions and also are
wanting to be kind of upskilledto be able to do more per unit
of time than they kind of do.
So again, I think, I thinklabour is a big pain point.
(16:32):
I think it's described typicallykind of in an abstract way and
you really need to think aboutlike,"Who's doing the work?" And
like, like I, I, I willencounter crews all the time
where like, you know, there'llbe a father, mother, son or
daughter team.
And like the parents are workingincredibly hard cause they want
their kids to be better.
And then they'll pull their kidsin the field to show their kids
how hard field work is toinspire their kids, to do
(16:55):
something else or to work harderin school or do something.
And so labour is a big painpoint and the blind spot in all
that is there are people workingon these farms, you really gotta
go talk with them to understand,basically to understand their
dynamics.
Mitchell Denton (17:05):
Absolutely.
So, when it comes to food lossand sustainable farming, what's
the biggest area your team arecurious about and why?
Charlie Andersen (17:15):
The English economist, Thomas Malthus, he
talks about how at some point,all, all populations reach the
point at which they're consumingall resources or they're over
consuming resources in theenvironment can no longer
sustain them.
And I think that in the case ofpeople, if you fast forward the
clock on where human populationis going, in the next couple of
years, or say the next 30 yearsor so, we are supposed to reach
(17:39):
the point where we are consumingthree X, what the planet
produced in 2010, which, whichobviously is not going to
happen.
And so to me, what I'm mostcurious about, I think, I think
in the past we've had themechanical revolution, we've had
a chemistry revolution, we'vehad a, a genetically modified
organisms revolution and allthose things.
(18:00):
And to me, what I'm most curiousabout is how big of a picture
can automation play in basicallydoing three X more in food
production than what we're doingtoday.
And, and if you, if you thinkabout like, what do you do in
your, what do you do in yourgarden?
When you see a beetle eating theleaf of a tomato plant, well you
squish it and you do that on aplant by plant basis, you're,
(18:21):
you're manipulating anindividual thing.
You get into big production Ag,you can't do that, you've gotta
do the same thing on everything.
I think that being able to seesomething and behave very
specifically to it in real timehas this huge potential to alter
the way we actually producefood.
And I'm very curious about howthat takes place.
(18:42):
And then the final question andall that is,"is all that, all
that done by one company?" And Idon't think it is.
I think it's actually done bymany, many different companies
and some will be buildingmobility, others are gonna be
building things around theneural networks to identify
particular diseases and there'dbe ones working on manipulation
and ones doing distribution.
Um, so yeah, there's a lengthylist of questions to what was
(19:02):
probably intended as a 30 secondanswer, so those are something
of the things that are tricklingthrough my mind.
Mitchell Denton (19:07):
No, this is the good stuff.
This is why I asked thequestions.
So continue on with thisthought.
Is there a particular group orinnovation within the industry
that you're excitedly keeping awatchful eye on?
Charlie Andersen (19:19):
So, going back to the layers comment, I think
there's a, there's a groupcalled Western Growers
Association.
And they have a perspective onautonomy that, that things are
ultimately gonna be built inlayers.
Um and, I really share thatperspective.
I think that that will also takeplace, um, at the same time,
with the way the industry istoday, a lot of the groups are
(19:42):
very reticent to work withothers, because it's unclear
who's a competitor and who's a,who's a, who's a friend, who's a
friend who's a fo is kind ofunclear.
Um, and so what I'm particularlyinterested in is following the
work that Western GrowersAssociation is doing to
encourage layers and then tryingto figure out what we can do as
a company to build the ultimatemobility platform on top of
(20:04):
which other companies mightbuild their manipulation system
or crop perception system, or...
I had a guy email me today witha, with a system that's supposed
to navigate around and feedanimals.
There are all of these funkyideas where I don't think that
one company does them all.
I think they're actually layers.
And I'm kind of curious how theindustry and how companies in
the industry can advance that.
Mitchell Denton (20:26):
Yeah.
Yeah.
So then what's one thing youwish you'd known when you began
your career in developingautonomous farming robots?
Charlie Andersen (20:35):
Um, I think it's just really hard and that's
that's, um, it's, it's hard.
People talk about barriers toentry and, and patent protection
and, and things like that.
And, and the realities ofbuilding these systems is so
incredibly hard.
I think that had I known thatfrom the outset, I probably
(20:57):
wouldn't have done what I'mdoing today and it probably
would be...
like, I I'm glad that I'm doingtoday what I'm doing today, but
that, but that said, I thinkit's really, really hard.
And I think just kind ofrecognition of what's the stuff
that is, it's not obvious fromthe outset, what is going to be
hard as you get into it.
Mitchell Denton (21:14):
Yeah.
Absolutely.
Absolutely.
So Charlie, we are unfortunatelycoming to a close, but as this
episode draws to a close, is themain point you want the
listeners to take away?
Charlie Andersen (21:26):
Yeah, so I think, people are kind of oddly
good at predicting where theworld is going in 10 to 20
years, but really, reallystruggle to predict how do you
win in years 1 through 5.
And to me, the main point, atleast as it, pertains to my
company in this topic.
Is that I think that in 10 to 20years, you're gonna see millions
(21:47):
of robots doing a variety oftasks on farm and elsewhere.
I think that the approach thatwe are taking, beginning with a
mobility platform, starting invineyards and nurseries and
berries is a unique approachthat appears to be proving
successful today.
And that if companies areseeking to build layers around
(22:10):
that require mobility, requireperception or, or require moving
manipulation from A to B, wewould love to partner with them.
And then I think that again, Ithink fast forward two decades
from today, and again, the sameway that you have a Roomba
navigating through your kitchen,vacuum cleaning.
I think you're gonna have tonsof small autonomous systems in
(22:33):
the world's largest industrydoing a whole host of different
tasks.
And so it's almost like we'resitting in, we're sitting in
1977 or 78 as early, early maintrains and PCs are emerging and
we're trying to envision Twitterand that's a really, really
exciting place to be.
But also we're very much kind ofpredicting something before it's
(22:55):
happens, which again, exciting.
Paving the way for a future,solving huge problems, but also
a, uh, an unpredictable place tobe in the world.
Mitchell Denton (23:02):
Absolutely.
I look forward to seeing whatlays ahead for the next few
years.
Charlie Andersen (23:06):
Yeah, me too.
Mitchell Denton (23:08):
Well, that's all for today's episode"Let's
Talk Farm to Fork".
Thanks for listening.
And thank you, Charlie, forjoining me today.
Charlie Andersen (23:14):
Great, Mitch.
Thank you so much, we reallyappreciate being on.
So thank you.
Mitchell Denton (23:17):
If you'd like to know more about Charlie and
Burro, check out the link andthe description on the episode,
make sure to subscribe to thepodcast so that you never miss
an episode.
And don't forget to leave areview and share with your
friends.
Until next time you've beenlistening to"Let's Talk Farm to
Fork", a PostHarvest podcast.
Voiceover (23:32):
We appreciate you joining us for this episode of
let's talk, farm to fork, besure to rate, review and
subscribe.
Also, if you would like to learnmore about how you can
practically play your part inmaximizing fruit and vegetable
supplies, whether you're asupplier, consumer, or anyone in
between the farm to forkjourney, visit PostHarvest.Com
(23:55):
and try out their free onlinecourse library today.
Popular Podcasts
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
24/7 News: The Latest
The latest news in 4 minutes updated every hour, every day.
Therapy Gecko
An unlicensed lizard psychologist travels the universe talking to strangers about absolutely nothing. TO CALL THE GECKO: follow me on https://www.twitch.tv/lyleforever to get a notification for when I am taking calls. I am usually live Mondays, Wednesdays, and Fridays but lately a lot of other times too. I am a gecko.