Congratulations! Looks like an interesting project!
replies(1):
Here's a video: https://www.youtube.com/watch?v=zCNmNm3lQGk.
Interfacing with existing excavators for enabling remote teleop (or autonomy) is hard. Unlike cars which use drive-by-wire technology, most of the millions of excavators are fully hydraulic machines. The joysticks are connected to a pilot hydraulic circuit, which proportionally moves the cylinders in the main hydraulic circuit which ultimately moves the excavator joints. This means excavators mostly do not have an electronic component to control the joints. We solve this by mechanically actuating the joysticks and pedals inside the excavators.
We do this with retrofits which work on any excavator model/make, enabling us to augment existing machines. By enabling remote teleoperation, we are able to increase site safety, productivity and also cost efficiency.
Teleoperation by the operators enables us to prepare training data for autonomy. In robotics, training data comprises observation and action. While images and videos are abundant on the internet, egocentric (PoV) observation and action data is extremely scarce, and it is this scarcity that is holding back scaling robot learning policies.
Flywheel solves this by preparing the training data coming from our remote teleop-enabled excavators which we have already deployed. And we do this with very minimal hardware setup and resources.
During our time in YC, we did 25-30 iterations of sensor stack and placement permutations/combinations, and model hyperparams variations. We called this “evolution of the physical form of our retrofit”. Eventually, we landed on our current evolution and have successfully been able to train some levels of autonomy with only a few hours of training data.
The big takeaway was how much more important data is than optimizing hyperparams of the model. So today, we’re open sourcing 100hrs of excavator dataset that we collected using Flywheel systems on real construction sites. This is in partnership with Frodobots.ai.
Dataset: https://huggingface.co/datasets/FlywheelAI/excavator-dataset
Machine/retrofit details:
Volvo EC380 (38 ton excavator)
4xcamera (25fps)
25 hz expert operator’s action data
We’re just getting started. We have good amounts of variations in daylight, weather, tasks, and would be adding more hours of data and also converting to lerobot format soon. We’re doing this so people like you and me can try out training models on real world data which is very, very hard to get.
So please checkout the dataset here and feel free to download and use however you like. We would love for people to do things with it! I’ll be around in the thread and look forward to comments and feedback from the community!
The Looming Disaster Under America's Biggest Oil Field [video] - https://news.ycombinator.com/item?id=45361022 - September 2025
Texas has thousands of abandoned oil and gas wells. Who is responsible for cleaning them up? - https://www.texastribune.org/2025/05/08/texas-orphan-wells-e... - May 8th, 2025
The Rising Cost of the Oil Industry’s Slow Death - https://www.propublica.org/article/the-rising-cost-of-the-oi... - February 22nd, 2024
Well plugging SOP:
Locales who don't want their aquifers contaminated will also be motivated in the near term to get this work done. They would be great test cases for proof of value of this automation imho.
(think in systems)
If you would be so kind as to suggest resources so that I can better educate myself in this domain for any missing nuance, I am open to any and all resources, including me traveling on my own dime to speak with a subject matter expert in person (who I am willing to compensate at a reasonable hourly rate).
The only metric that matters at the end of the day is how to print more money i.e. drill more oil. Literally nothing else matters, and compliance goes to the lowest bidder to make the problem go away. Right now that means playing nice with the whitehouse and hopefully bypassing the rest of the pesky EPA. I assure you not a single person in oil and gas likes the EPA, nor the infamous Subpart W.
I've actually spent a decent amount of time running an excavator, as my Dad owns a construction / road building company. It was a great summer job!
An important note about the pilot hydraulics is that they _provide feedback to the operator_. I would encourage any system that moves these controls on behalf of a remote human operator or AI to add strain gauges or some other way to measure this force feedback so that this data isn't lost.
The handful of "drive by wire" pieces of equipment that my Dad or other skilled operators in my family have ran were universally panned, because the operators are isolated from this feedback and have a harder time telling when the machine is struggling or when their inputs are not sufficiently smooth. In the automotive world, skilled drivers have similar complaints about fully electronic steering or braking systems, as opposed to traditional vacuum or hydraulic boosting approaches where your foot still has a direct hydraulic connection to the brake pads.
I imagine an excavator, meant to touch and dig through things, and lift things, benefits from force feedback for the same reason VR would.
Have you played those VR sword games? BeatSaber works great because you're cutting through abstract blobs that offer no resistance. But the medieval sword-slashing games feel weird because your sword can't impact your opponent.
I saw a video recently of a quadcopter lifting heavy objects. When it's overloaded, it can't maneuver because all its spare power is spent generating lift to maintain altitude. If the controls had force feedback, the copter's computer could tell you "I'm overloaded, I can't move" by putting maximum resistance on the sticks.
There was a YouTube video recently of an AI-assisted digger making a wall out of the concrete rubble from a demolition.
I believe the applications for really smart excavators must be huge. Sounds like this might be a step on that voyage.
One big advantage would be cameras mounted on the boom and rear view cameras, as many machines have obstructed views.
I ask in all seriousness since, for example, retrofitting regular semis to electric requires millions and millions just to get started
I'd like to get a chance to talk to you and your Dad to get feedback. How do I reach you? My email is contact at useflywheel dot ai
I have a Cat 289D skid steer I would happily contribute to the effort if you guys move into the compact equipment space (compact being a relative term, as my machine is only 6 tons compared to your 38 ton machine)
https://x.com/jash_mota/status/1969091992140304703
I think force feedback is key for small excavators, but not really true for 25+ tons excavators. Hence how easy it is for operators to accidentally kill someone with it.
Also, teleoperation is likely to produce lower-quality operation data than hooking up to locally operated excavators. Just a thought.
/? Zonal isolation Wikipedia: https://www.google.com/search?q=zonal+isolation+Wikipedia :
> Well cementing, Completion, Squeeze job, Cement bond log, Casing (should prevent fluid from contaminating e.g. aquifer zones)
Orphan wells: https://en.wikipedia.org/wiki/Orphan_wells :
> they estimate there are 29 million abandoned wells internationally
Orphaned wells in the United States: https://en.wikipedia.org/wiki/Orphaned_wells_in_the_United_S... :
> According to the Government Accountability Office, the 2.1 million unplugged abandoned wells in the United States could cost as much as $300 billion
So even if the electric system fails completely, you can still actuate the brakes.
I cannot imagine this being useful to me unless the virtual operators cab closely mimicked an actual machine. It would have to have audio from the machine and be on a platform that tilted relative to the real thing. It would also need 270 degrees of monitors with a virtual mirror to see behind. On the front monitor, minimally, would need the to see vertically up and down too.
I also imagine all of this would be more useful to seasoned operators who can do most things on excavators in their sleep (definitely not me lol)
Is that different than what you are doing now?
related, this cool photo: https://x.com/jash_mota/status/1969635994220839095
Construction excavation workflows tend to be different and more varied (hence you would see more variations in the machines/attachments available for this industry). And so far there's no solution which just works or is plug and play. This is an attempt to solve that.
And we believe this is great time to do so due to market demands too. No way Gen Z is going to do these jobs when you can make money being delivery partner/influencer, etc. The high-certified, high-skilled workforce is going to shockingly shrink in some years.
So if we are able to have really good autonomous safety layers to ensure safe movements, and dynamically resize remote teleop windows, you'd make the operator more efficient. So while we stream 360 degree view, we get creative in how we show it.
That's on the vision side. We also stream engine audio, and do haptic feedback.
Takeuchi are interesting! Rare ones to have blades even on bigger sizes - is that why you got one?
Skilled humans have a tendency to fully engage all of their senses during a task. For example, human drivers use their entire field of vision at night even though headlights only illuminate tiny portions of their FoV. I've never operated an excavator, but I would be very surprised if skilled operators only used the portion of their vision immediately around the bucket and not the rest of it for situational awareness.
That said, UI design is a tradeoff. There's a paper that has a nice list of teleoperation design principles [0], which does talk about single windows as a positive. On the other hand, a common principle in older aviation HCI literature is the idea that nothing about the system UI should surprise the human. It's hard to maintain a good idea of the system state when you have it resizing windows automatically.
The hardest thing is going to be making really good autonomous safety layers. It's the most difficult part of building a fully autonomous system anyway. The main advantage of teleop is that you can [supposedly] sidestep having one.
It's like driving a Ford F150 without backup camera. You'd add the backup camera upfront, and not display the back view at the back window.
It's definitely challenging and we're far from something that's perfect. We're iterating towards something that's better everyday.
Yes that is precisely why - makes for a much more versatile machine. TB180FR - it’s med-small, about 10 ton.
Those workflow numbers come from multiple observations at different sites, one of the examples is this: https://www.youtube.com/watch?v=orEsvu1CS64
I wish to talk to you because it's rare sight someone has a Takeuchi - is there a way to connect? My email is contact at useflywheel dot ai
I disagree and here's a couple of reasons why I say that:
1. What am I going to do with the time between releasing control and regaining it from the autonomous control?
2. In that break of workflow my first thought is it will cause a break in my concentration.
3. When I am swinging back from the truck to the trench the bucket is naturally in my control. It seems that in autonomy mode the transition from autonomous to my control would be very unnatural and choppy. I suppose with time it would be okay but man seems to violate the whole smooth is fast concept.
I'll shoot you an email.
Sigh. No. Actual TAM is $0 which is why these wells are orphaned
For contrast, maritime shipping IMO (my current obsession) has set a $100-$400 carbon price. So now the efuel market a realistic $10B ZNZ pot to aim at.
The range of skillset on these things is large, there are 2 dominant (fairly swappable - meaning most machines do both) different operating modes (excavator / backhoe) and I see that operators have a specific one they are best with.
Honestly, when I see a real pro using one of these machines I think this is one area AI is not going to win at soon - in the real world there's a whole support crew working with the excavator operator
This leaves remote operation, which just makes no sense at all. The cost of one guy going to a construction site is never going to be more expensive than retrofitting a fleet of excavators with this hardware and building a remote operating center. Additionally these should obviously not be allowed to be used at construction sites, since remote operation in such a dangerous environment adds a totally new layer of hazards. Direct communication between operators, verbally and visually, is extremely important, to operate an excavator safely.
If there's a failure of the electrical supply to the brake ECU, or another fault condition occurs, various valves then revert to their normally-open or normally-closed positions to allow hydraulic pressure from the pedal through to the brake cylinders, and isolate the stroke simulator.
Because the engine isn't constantly running and providing a vacuum that can be used to assist with brake force, the system also includes a 'brake accumulator' and pump to boost the brake pressure.
Reference: https://pmmonline.co.uk/technical/blue-prints-insight-into-t...
I don't know for certain, but I would assume that other hybrids and EVs have similar systems to maximise regenerative braking.
It's been over a decade since I last operated an excavator, so grains of salt as usual - but I'd say it should be manual, or at least semi-automated. You need to take care where you unload the bucket on a truck, to avoid its weight distribution being off-center, or to keep various kinds of soil separated on the bed (e.g. we'd load the front with topsoil and fill the rear with the gravel or whatever else was below.
But... I assume you're intending to run on extremely large sites such as highway construction, open pit mines and the likes primarily? Because my experience (if a bit dated cough) is running small 750kg baby excavators under sometimes extreme space constraints - digging trenches for telco in urban and rural areas, which often enough meant having to work with 5-10 cm distance to walls, lighting posts or other infrastructure, and directly next to workers shoving soil into the bucket. Will you add stuff like 360° camera vision, LIDAR etc. to make that safe and help a remote/AI operator, or are you planning on large sites with less danger potential only?
That's because semis - just like cars - are road legal and everything has to be done by the books. The hard part isn't swapping out the engine and mounting a battery pack, car modders have done that for decades for funsies, the hard part is getting it certified for roadworthiness.
On construction sites, particularly ones fully on private property, no one gives a fuck about the equipment, at least not until someone gets hurt, maimed or killed.
And last but not least, my car can’t keep lane and can’t drive itself safely in autonomous mode for 50 miles straight on clear day on highway. That’s state of art vision only system in 2025.
The salary of the skilled guy is laughable compared to heavy machinery costs. I was in a quarry on Tuesday. Two guys were operating 7000000€ machinery there, their salary is rounding error in the whole operation. Fuel over the year costs more.
So in reality, CANbus control should be no different than hydraulic control to your system - just another style of I/O
I am curious if something like this is an opportunity for a whole new type of controls and feedback. Since the operator doesn’t have to be in the excavator physically they could take on any position: standing, sitting, lying down, etc. Instead of sending haptic feedback to the joystick it could be sent to a vibrating wrist band. You could hook up the equivalent of a Nintendo Power Glove to have the scoop operated by the operator simulating scooping action. Turning the excavator can be controlled by the operator turning their head and moving it around can be done by the operator walking on an infinite treadmill. Motor strain can be done via color of light or temperature rather than sound. You could have a VR helmet that can also show you a birds eye view from a companion drone, overlay blueprints, show power and water lines, measure depth, etc. I don’t know if it is possible but maybe you could even measure soil composition somehow to show large rocks, soft soil that is dangerous to drive over, inclination angles where the excavator is about to drive, etc.
I imagine skilled operators prefer familiar controls but perhaps there are interesting improvements unlocked by exploring alternatives. It might also fundamentally change how accessible it is for non-professionals to use these machines. I rented an excavator from Home Depot a few years ago to dig a foundation and the learning curve was not shallow. I wonder if a more “natural” interface would help keep people safer.
And I only say this because I think this is an interesting area to pursue so I hope you're successful with it. But a focus on safety will be of paramount importance.
Do you want to sell Microsoft Teams to the executives or do you want to give joy to the people who actually use the product?
I'd like to have a chat with you if you're up for it: contact at useflywheel dot ai
You might be interested in the work of Peter Corke also, he's automated horizontal mine shaft loaders and huge drag line shovels in his research:
https://www.youtube.com/watch?v=YUb9_Ysd2Hw
I think he used a different approach than you do, using visual servoing to get feedback and data from a camera. Maybe there's some value in combining both approaches, learn to control a machine from an operator, and also keep track of what is being moved with a camera to add another layer of control.