[HN Gopher] Launch HN: Polymath Robotics (YC S22) - General auto...
___________________________________________________________________
Launch HN: Polymath Robotics (YC S22) - General autonomy for
industrial vehicles
Hey HN, I'm Stefan, one of the founders of Polymath Robotics
(https://www.polymathrobotics.com) and formerly of Starsky Robotics
(YC S16). My co-founder is Ilia Baranov, a career roboticist. We're
building general autonomy software for industrial vehicles. We've
just come out of stealth with a full autonomy stack freely
available in sim online. Whether it's a tractor on a farm or a 400t
dump truck in a mine, we make it easy for you to make it
driverless. Where before you would need an industrial vehicle,
$25-150k in sensors + compute, and 6-18 months of building time,
now you can start building applications that command autonomous
robots right away. See a demo here:
https://www.loom.com/share/852d54744d45452d926b9016f61f5e43. Two
big things are hard about automating industrial vehicles: first,
robotics is deceptively hard. But also, industry is nitpicky. These
two together are too much for most startups. That is, if you put
all your energy into the first--the noble effort of getting the
robots to actually work-- the second will end up killing you. We
learned this the hard way at Starsky, and what we're currently
working on at Polymath is a way out of this dilemma. At Starsky,
we were working on autonomous trucks. We knew that was a hard
product to build, but I didn't really have perspective until I went
and hung out with SaaS companies afterward. My SaaS friends use
horizontal services at every layer of the stack. Payments? Just
plug in Stripe. Messaging? Twilio. Libraries and tools exist for
everything. Your thing goes a lot faster when you can just buy the
rest of the stack. Contrast that with Starsky, where we were
building our own robotics stack completely from scratch. That meant
the autonomy itself (our actual product, and really complicated on
its own), but also custom teleop, a drive-by-wire system, hardware
abstraction layer, and fleet management system to orchestrate all
the trucks via an API. Each of those things could be a company in
itself! Imagine trying to debug a stack like that when something's
not working. That's sort of just how robotics is today. Like
software in the 80s, everyone's rebuilding the whole stack for each
new project. So the tech gets super complex, brittle, and
unadaptable. In fact, an open secret in the robotics world is that
most demo videos you see are "cooked," because the robots are so
unreliable in the field. I got to know many of the folks building
industrial autonomy vehicles from 2016 onwards, and saw a
depressing pattern. Brilliant, mission-driven engineers would get a
start with a healthy seed round from investors who thought it was
"just" an execution problem. After 18-30 months the teams would
have a prototype that somewhat worked, but what they _wouldn't_
have yet was the commercial traction needed to justify more
fundraising. That brings us to the other half of the dilemma:
industrial customers are nitpicky. When it comes to scaling an
autonomous vehicle POC (proof of concept) with a large industrial
company, they're surprisingly unimpressed with autonomy. Sure - the
first time they see a driverless vehicle their jaws drop and they
ask about safety. But like everyone else, they quickly assume it
"just works" and start asking whether it will integrate with their
Oracle instance. Then they start nitpicking the specific way the
tractor drives across the field / the luggage tow stops on the
apron / the dump truck pulls up to the processor / etc etc. In
other words, after the initial POC, industrial autonomy stops being
sexy-super-hard-technical and starts looking like Enterprise SaaS.
Except by then the team has spent 2 years heads down making
autonomy (the hard part!) actually work rather than talking to
customers. As a result, they're not up on the top 20 things
customers care about and they don't end up with product market fit.
Few startups make it out of that pincer squeeze. All this to say
... what we're building at Polymath is a shortcut to autonomy for
industrial vehicles. We make it so you spend less time building /
maintaining undifferentiated basics, and focus instead on the 5-10%
of the application that's hyper specific to your industry / vehicle
/ customer. Just like our friends in SaaS. Since we're _just_
building the autonomy layer, we can focus on getting the tech
reliable, stable, and scalable. Our users can build their own
custom behaviors, or integrate with apps, or whatever it is that
makes their robot actually useful, on top of the Polymath autonomy
core. The software can be installed on virtually any large outdoor
vehicle, as long as it operates in a controlled environment.
Focusing exclusively on closed environments is partially a cheat
code. It lets us assume the vehicle can come to an immediate stop
if there's trouble, or be teleoperated by a human in dicey
situations--all the constraints that mean we _don't_ have to be
Waymo or Cruise. Polymath autonomy includes localization,
navigation, controls tuning, obstacle avoidance, and a safety
layer. Importantly, we also built a hardware abstraction layer,
which lets the whole thing work across different vehicles and
sensors. One thing we're doing differently this time around is
buying (rather than building) parts of our solution wherever
possible. Again, part of that "make robotics more like software"
thing. So we're using Formant for teleop, Gazebo for sim, and for
customers that need hardware installation, we have a partner called
Sygnal that does awesome integration and retrofit work. (And,
almost obviously, we're built on top of ROS [Robot Operating
System, the standard framework for building robots). We also have
our own demo vehicle, a tractor affectionately nicknamed
'Farmonacci', that we use to run unmanned testing daily. You can
see a shiny demo video of it here: https://youtu.be/bP0mNG53bVw And
now the part I'm most excited about... You can start building on
top of Polymath autonomy today, for free, in sim, with a tool we
built called Caladan (yes, the name is Dune-inspired). Caladan is
a set of simulated vehicles and environments where you can interact
with Polymath's autonomy via Rest API. That means you can build
autonomous vehicle behaviors and applications in your preferred
programming language, without having to touch ROS. So, even non-
roboticists can build an autonomous vehicle application pretty
easily. To my knowledge, we're the first to build an autonomy
product that's this accessible, and especially something that you
can use for free (it's funny that roboticists, a group least
interested in talking to sales people, is super forced to). We
built Caladan by bringing our autonomy code into a standardized
Gazebo environment, with a Rest API that allows you to command it
in any language (without needing to know anything about ROS). The
cool thing is, you can transfer the same code you write with
Caladan to a real vehicle. We've tested it out with Farmonacci, and
we'll select people who are hacking on top of our simulated
vehicles and give them testing time on Farmonacci as well. Part of
the idea for Polymath is to take robotics off of 'hard mode,' and
help teams build robots that are stable and reliable right from day
one. For now, it's entirely free to use Caladan. Since each
instance is a cloud-GPU, in the next couple of weeks we'll ask
people to pay if they want consistent access (but there will always
be a free version). We want to make our money automating your
actual robots, and we'll also charge if we have to do too much
custom stuff for you in sim. But, of course, we have startup-
friendly pricing if you talk to us. So please, sign up for Caladan
at polymathrobotics.com and mention that you came through
HackerNews (we'll prioritize spinning up your instance if you do).
We can't wait to see what you all build. We'll be around in the
thread and look forward to your comments, ideas, and feedback!
Author : stefan8r
Score : 119 points
Date : 2022-08-01 15:49 UTC (7 hours ago)
| pranavjoneja wrote:
| I work in robotics, I understand that every robotics company
| builds substantially similar core autonomy for different
| industrial vehicles, so I definitely see the value of what you're
| creating. However, every company needs to figure out how their
| autonomy will handle their specific vehicle's dynamics and their
| specific physical environment. For vehicle dynamics, they have to
| model things like wheel slippage on rough terrain, articulating
| joints on multi-axle vehicles, braking distance while hauling a
| load. For physical environment, they have to figure out how dust,
| fog, and poor lighting conditions affect their sensing and
| perception. Do you intend to make custom sim vehicles for each of
| your customers? Will you simulate each customer's particular
| camera/lidar/other sensor in their specific environment?
| stefan8r wrote:
| This is a good, well thought out point that I 60% disagree with
| (respectfully, of course). I think you're absolutely accurate
| in describing how robotics is today, and you're definitely
| partially correct about how it will remain, but I think you're
| biasing towards thinking robotics (as a field) is exceptional
| to the types of progress that have happened in software.
|
| To unfairly simplify that assertion, it reminds me of a founder
| who once told me that "robotics will never be as easy as
| software. It's just harder and will always be so."
|
| I don't know if I think each autonomy company needs to figure
| out vehicle dynamics any more than I think each company needs
| to figure out their cloud infrastructure. At a certain scale
| (and amount of success) you will certainly need smart people
| thinking about it, but you can get pretty far on a 90% standard
| AWS instance. Things like wheel slippage are challenging, but
| their challenging in similar ways across vehicle types (but
| different from other tasks you need to work on when building
| that higher level autonomy).
|
| Similarly, if you assume you can safely stop when there's
| danger, there are a relatively finite number of environmental
| conditions you should operate in - which we can build,
| maintain, and improve "once" as opposed to making every mining
| OEM or Ag autonomy shop build from scratch. In time, there
| might be certain portions of this stack that you can swap out
| with your own (or with some other company that's better at
| seeing in the fog, for example); but I fundamentally don't
| believe that every robotics company needs to solve all of these
| hard problems well on their own for every application.
|
| Re:Sim - for paying customers we are putting their specific
| vehicle (and sometimes their environment) as a part of the
| offering. We're also using sim to help figure out how to
| position sensors (which will be another cool thing that we want
| to show at some point).
| j4pe wrote:
| Congrats on the launch, Stefan. That is a heck of a nice wrap on
| that tractor. Best of luck!
| stefan8r wrote:
| Thanks so much! We had a fantastic designer, and our
| marketing/ops/cust success/everything else lead is really way
| better than we deserve!
| hazrmard wrote:
| Nice work! Are you using Gazebo for simulations for training at
| the back-end? Or as a user-facing interface to demo whatever
| automation they want to deploy in a sandbox?
| stefan8r wrote:
| We are using Gazebo for working on controls (getting Caladan
| ready to launch also led to a number of big improvements in
| controls) but not for ML training.
|
| The point of Caladan is more for you to be able to build
| specific autonomy functionality without needing a vehicle, or a
| large plot of land, or a team to build a basic autonomy stack
| that works.
| stefan8r wrote:
| And, I should say, thanks for the kind words!
| fallingmeat wrote:
| Have you explored using a formal verification tool to prove out
| the safety/liveness properties of your (or the end user's)
| autonomy specifications? Could you model the system in something
| like Spin/NuSMV/PRISM and then ensure that certain properties
| hold (useful states are reachable and dangerous ones are not)?
| iliabara wrote:
| Hey,
|
| No, we haven't looked into formal tools like that, good
| suggestion! TBD on if these approaches bode well for real world
| robotics, (due to model complexity and model/real world fit
| problems) but at least there seems to be some applications to
| path planning and controls:
| https://ieeexplore.ieee.org/document/5509686
|
| I'll pass it on to the controls team!
| ModernMech wrote:
| Honestly wish you all the best here! Truly, it's great that
| you're trying to simplify the deployment of robotics, because
| that would be great for everyone.
|
| One thing I have to say looking at your website, is that is has
| serious "Underpants Gnomes" vibes.
|
| 1. Build in sim 2. Test in sim ... 3. Deploy on a real robot
|
| Taking something from simulation and having it work
| "effortlessly" (as your marketing puts it) is sort of the holy
| grail of robotics. It's something that has confounded researchers
| and roboticists for a long time, so I'm a little bit skeptical as
| to whether your product actually lives up to the promises made in
| your marketing material. It would help if you showed more demos
| of what this means in a practical sense. In the video on your
| website it shows a simulated tractor, and then a tractor moving
| in an open field with no obstacles. This is pretty much the best
| case scenario, but how does it actually perform in more realistic
| scenarios?
|
| Going into your FAQ a little, it seems to suggest the process
| isn't so seamless: We've built Polymath with the
| goal of a seamless transition from sim to reality (other than
| necessary-but-minimal tuning of controls).
|
| "Necessary-but-minimal" is kind of understating how difficult
| sensor calibration and controller tuning is. It's all the
| difference between a simulated world and the real world (and also
| necessitates the need for controls and perception experts, which
| your marketing seems to imply are not needed or minimally
| necessary with your product). I'm curious how your product makes
| this process easier.
|
| It appears like your value-add is that your product simplifies
| the whole ROS tech stack to some degree, but to me I would
| imagine transitioning from sim to reality without much work would
| imply that you have made real advancements in simulation
| technology. Is that the case? Or does your product mostly address
| improvements in the development experience?
| stefan8r wrote:
| Ilia gave you the more real (and specific answer) but I just
| want to call out that I love the Underpants Gnome reference. I
| used to cite it a lot and was frustrated by how many times I
| had to explain it.
|
| Sim =/= sim =/= sim. By which I mean - when some people say
| "build autonomy in sim" they mean lots of different things.
| Sometimes they mean solve all ML and data collection problems
| in a simulated world. We don't mean that.
|
| When we say build and test in sim, we really mean that for just
| the earliest phases. Essentially - if you wanted to build Bear
| Flag Robotics 2.0 you could take our example app (lightweight
| Python app to tell a tractor to till a field), meaningfully
| improve it, show it to farmers to get LOIs, raise money, buy +
| outfit a tractor, and then put our autonomy on that tractor.
|
| In that end state the behaviors you built out in Sim would
| still mostly work on the real tractor (same API commands both)
| and you could end up modifying those behaviors the way you
| would need to make them work in the real world. We would also
| be working with you closely to make sure our product is working
| well, solving new problems, and probably doing things that
| don't scale to help you be successful.
| simonebrunozzi wrote:
| Had to look it up [0], as I didn't know it.
|
| Side note: I'm always happy to learn a new reference, but most
| of them are heavily US-centric, and for people like me who
| didn't grow up in the US, and live or lived in the US in their
| adult life, sometimes it's a bit too frustrating, because
| there's just too much of it going around.
|
| The worst of all is when the reference is killed by Italian
| dubbers/translators (in Italy you can rarely watch TV series or
| movies in their original language, which is very comfortable,
| but deeply damages your ability to understand cultural
| references, which most non-US foreigners would get because they
| watch the original English version of everything).
|
| Anyway, just to give all of you some new perspective of how
| these things are perceived by some foreigners.
|
| [0]: https://en.wikipedia.org/wiki/Gnomes_(South_Park)
| iliabara wrote:
| Hello,
|
| You are asking about the FAQs here:
| https://www.polymathrobotics.com/product
|
| We are actually a hardware and real robots company first! Our
| simulator efforts are for two purposes: 1. Allow more people to
| try out our autonomy core, and build on top of our API 2. Allow
| our own developers to run testing and tuning in sim.
|
| To your point, we don't expect tuning to purely happen in sim.
| However, we did have our senior controls engineer just recently
| tune up a controller in sim for Caladan, and later deploy
| practically the same thing to the real vehicle, leading to much
| smoother steering commands. We'll write about that in detail in
| the future.
|
| Our work is to ensure that API commands that are sent in sim,
| behave as close to identically as possible on real vehicles,
| thereby allowing people who build on top of us to focus on
| higher level software stack (business logic layer, etc). Hence,
| users of our API don't need to have any robotics experience,
| they simply command the vehicle to do something, and we ensure
| it gets done. (and our team is comprised of perception,
| controls, ML, etc engineers)
|
| The details of how this is done will be a future writeup, but
| the summary is that we pass sensors through a Hardware
| Abstraction Layer (HAL), along with kinematic/dynamic
| configuration and data about the vehicle. This allows the
| global and local planners to plan for a more generic vehicle
| (ex: Ackermann steering vs differential steering), while the
| HAL ensures that the planners don't generate unfeasible or
| unsafe commands.
|
| Let me know if the above answers your questions!
| ModernMech wrote:
| When you say this: they simply command the
| vehicle to do something, and we ensure it gets done. (and our
| team is comprised of perception, controls, ML, etc engineers)
|
| Do you mean you're offering control and perception
| engineering as a service?
| iliabara wrote:
| No, sorry, let me be more clear.
|
| Users of our API can send high level commands (ex: go to
| GPS coordinate X), and our software (on vehicle) will
| ensure it gets done.
|
| Our software is built by a team of roboticists, including
| ML, controls, etc. The software we write ensures that the
| real world vehicle responds almost identically to the
| simulated one.
|
| There are of course limitations, hence we do a
| commissioning step where we ensure the work we've done in
| simulation for a particular vehicle (sensor locations,
| localization fusion of sensors, controls tuning due to
| kinematics/dynamics etc) are tested and tuned on the real
| vehicle. This is done before the real vehicle is put into
| service, and remotely monitored (collection metrics on
| performance, status of sensors/actuators, etc).
|
| Cheers!
| stefan8r wrote:
| To add a somewhat easy sentance here - we're our actual
| product is delivered as SaaS (and it's not at Gmail
| pricing, it's more enterprise). Were you to become a
| customer we'd be pretty handholding with you to get the
| thing actually working.
|
| There is a perception stack and a controls tuning stack
| within that SaaS that we'd be delivering.
| ModernMech wrote:
| Okay thanks this clears up a lot! The ... in the process
| that I noted in my first post sounds like the handholding
| you're talking about.
| nitsuaeekcm wrote:
| Congrats on the launch! The novel (for robotics) business
| structure looks interesting. How are you planning on kickstarting
| the ecosystem? It looks like you need at least one or two
| competent companies above you on the stack before you can start
| getting real-world feedback. (1) Do you have in mind who these
| companies will be? Do they exist yet or do the need to be
| created? (2) One of the super difficult things about robotics is
| reconciling the difference between a clean sim and a messy world.
| How will you get feedback on how your robots are operating and
| iterate if there's an independent company sitting between you and
| the customer?
| stefan8r wrote:
| Thanks! It would be lovely if posting this one time in HN
| single handedly kicked off that ecosystem -> so everyone
| reading should quit their jobs and build robots /s
|
| More seriously - there are a surprisingly large number of
| groups out there building robots and looking for help. Some
| groups already have not-built-here syndrome, but our hope is
| that by being a free thing you can just initially build on
| people will be "Polymath Native."
|
| Your sim question is especially poignant. Our sales line is
| that reconciling sim:reality is our problem to solve for you.
| The more real answer is that we're specifically focused on
| vehicles in environments that are "relatively clean" - i.e.
| controlled (even if, in fact, they're a landfill). We're also
| only really selling to technical users - who are hopefully
| sophisticated to solve >0% of the problems.
| bluelightning2k wrote:
| Your post reminded me of the early Apple days. There's
| parallels there with robotics.
| captaindiego wrote:
| Looks interesting! Are you able to make any guarantees for
| determinism when replaying recorded data through your stack?
| iliabara wrote:
| Hey, Ilia here :)
|
| Not sure if the question is about the simulator Caladan, or
| about our autonomy core.
|
| For Caladan, we don't support playback of data currently. Do
| you have a use-case need for this?
|
| For the autonomy core, the localization, costmap generation,
| and path planner are all probabilistic to a more or less
| degree, so we can't guarantee determinism to any highly
| accurate degree. However, if the same data is played back over
| and over, the vehicle would react in basically the same way
| (perhaps not navigating to the exact same spot, but within a
| small tolerance). Same question here; what is your need/use
| case to have guaranteed determinism? Is it a safety question?
| (We can have a much longer chat there)
| captaindiego wrote:
| Thanks, I was talking more about the autonomy core side of
| things.
|
| So to narrow it down a bit more, my question is a bit tied to
| safety, but also to general development. Given a set of
| logged inputs from a machine that had a field issue X, am I
| able to reliably reproduce (hopefully deterministically) what
| happened on that machine? (and therefore what went wrong)
| bluelightning2k wrote:
| I think this is fundamentally interesting.
|
| I also appreciated the write up. Rooting for you! I think FAR
| more startups should be focusing on robotics and basically
| anything to do with meeting fundamental needs IRL.
|
| You did a great job with the description. Makes me want to get
| off the sidelines and build robotics on your API. (I have startup
| hyperactivity lol)
|
| Unrelated: do you have to be a YC company to do a Launch HN?
| stefan8r wrote:
| You should get off the sidelines! Post-Starsky I wanted to run
| away from HardTech / FrontierTech and just do "easy SaaS
| stuff."
|
| I was deeply upset to realize I was too broken to do something
| that "easy." (still, really hard). As a mentor of mine, Boom's
| Blake Scholl, has said - it's sometimes easier to do "hard"
| things because it's easier to get the motivation to work on
| them.
|
| Re:Launch HN - I think so? You can always do a Show HN, though!
| bluelightning2k wrote:
| Well said!
|
| I'm personally working on something hard in SaaS (automatic
| summary video after every Zoom/Teams SaaS demo).
|
| I think truly hard things are in a lot of ways easier for
| truly inventive engineers because it's an execution challenge
| but you basically know for sure there's a market after.
|
| Also hard things can be decomposed. If you solve one part (as
| you are doing) that's enough. So you can really niche down
| within something hard and still change the world
| stefan8r wrote:
| Ya video summary is nothing to sneeze at - I'll take my ML
| tasks as easy as determining if something is a person or a
| pixel /s
|
| Completely agree on decomposing hard things.
| orliesaurus wrote:
| Do I understand this right..:
|
| - You have a simulator, like idk The Sims world
|
| - You train a machine in this world, totally virtual
|
| - You deploy the trained machine on real hardware in the physical
| world
|
| - The machine works good enough that it can perform the task
| until it can't anymore and then someone remotes-in to fix it?
|
| Did I get this right or can anyone ELI5 to me? I mean it sounds
| really cool, in theory...
| iliabara wrote:
| Hey!
|
| We don't train in simulation (if you are talking about ML
| training). Our ML training is done purely using real world
| data.
|
| The simulator is to allow developers to "test drive" our
| autonomy core and API for free.
|
| We have real vehicles as well, but you can imagine it's more
| expensive, time consuming, and generally slower to let people
| test on real hardware. Hence, if people like what they see in
| sim, they can get in touch with us to deploy their code to real
| machines on a case-by-case basis.
| stefan8r wrote:
| To add to what Ilia said - re: - "The machine works good
| enough that it can perform the task until it can't anymore
| and then someone remotes-in to fix it?"
|
| The machine will work good enough for basic autonomy, but
| then the real application-specific work begins. Whether that
| work is you modifying the behaviors you're having us do, you
| routing those systems to humans to help out, or you
| complaining that our stuff sucks (and us trying to rapidly
| improve it).
| simonebrunozzi wrote:
| Stefan, I met you a few times in SF, and remember you - probably
| 5 years ago. Really liked how you tried to tackle the
| transportation problem at Starsky. We had a quite long chat one
| evening, at a birthday party of an Italian friend. I think we
| even played bocce together :)
|
| Good luck with your new company! Watched the demo; pretty cool
| stuff. Feel free to reach out to me if I can be of any help
| (starting a new VC fund), or even just as a sounding board ($my-
| hn-username @ gmail, or @simon on twitter).
| stefan8r wrote:
| Thanks so much for the note and the kind words. Would love to
| grab a coffee or something! My email is first @
| polymathrobotics.com, but I'll reach out as well!
|
| Maybe we can play bocce instead of coffee?
| iliabara wrote:
| Hey all, Ilia here.
|
| I just did a quick follow up with a demo of our API driving our
| real tractor, and simulated tractor, simultaneously.
|
| The API used is the same, and we are sending the same commands at
| the same time to each vehicle.
|
| Check it out here: https://youtu.be/86pBFbTHPOA
| stefan8r wrote:
| brushfoot wrote:
| You mentioned large vehicles - is there any support for small,
| e.g., use in a swarm?
| iliabara wrote:
| Hey, Ilia here :)
|
| This could be built, but unsure it'd make sense in terms of
| required compute on each small robot. What would be the use
| case you are interested in?
| stefan8r wrote:
| To add to this - a neat thing about swarm robots is splitting
| the compute load between robots and figuring out how
| different robots move in conjunction with eachchoter. We're
| just focusing on the software that sits on the robot itself -
| so any of that coordination would be above our layer
| nine_k wrote:
| I can imagine several autonomous trucks sharing large
| segments of roads, and splitting into a number of locations
| at the ends. Such vehicles could benefit from coordination on
| the shared segmets.
|
| I suppose that trucks serving most open mines work that way:
| they have to share the common spiral part.
| stefan8r wrote:
| Ish. To _probably_ annoy you and everyone on this thread,
| I'll tell you how this works for a "large publicly traded
| company that has autonomous vehicles in mines."
|
| Essentially they have a portion of the mine site designated
| as the "autonomous pit," which is the only place where
| autonomous vehicles can operate. Not all vehicles in the
| autonomous pit are autonomous (basically no one can
| automate the vast majority of industrial vehicles, which is
| part of what we want to solve). In order to be able to see
| these non-autonomous vehicles, this PubCo makes the mine
| buy a $20-50k transceiver to put on every non-autonomous
| vehicles (in addition to the $1m auton hw upgrade and
| $250k/yr in autonomy SaaS).
|
| These autonomous vehicles do have sensing, but they more
| rely on those transceivers to tell where vehicles they
| shouldn't hit are.
|
| So ya, sure, it kindof works like how you think it should.
| But in a worse way.
| nosequel wrote:
| This is really cool. I was on a team for the first and second
| DARPA Grand Challenge. The teams (like ours) who had to use
| actuators, pistons, gears oh-my for steering, acceleration,
| braking were at a huge disadvantage compared to the teams who
| were given the drive-by-wire access (CMU/Stanford & VW Touareg
| partnership(s)). It would've been really nice at the time to get
| the mechanical aspects all worked out and have a nice autonomy
| layer to use that was ready and tested. I applaud the work you
| are doing and know it is NOT easy. I also happen to own some
| construction equipment and can't imagine how hard it would be to
| interface with a dual pilot joystick configuration (think skids &
| dozers). It is a completely different way to think about travel,
| turning, bucket work, tipping weight. Sounds like you all have
| some really interesting tough problems to work on. Bravo.
| iliabara wrote:
| Thanks for the kind words, and awesome that you were on a DGC
| team!
|
| Absolutely, there is a ton of really interesting controls, ML
| and general software quality work for us to do.
| stefan8r wrote:
| Thanks for the kind words!
|
| Ya - I can't imagine how hectic it was for you guys. I remember
| hearing Josh Switkes talk about hand building radars for
| pre-2010 autonomy.
|
| Re:booms/buckets/etc: right now we're just focusing on mobility
| (making these systems drive from A to B), specifically because
| those systems are deceptively hard. FWIW I think the guys at
| Built Robotics have done some cool stuff on it, as have groups
| like Moog and FP Innovations.
___________________________________________________________________
(page generated 2022-08-01 23:00 UTC)