I wrote my master thesis on optimizing bicycle wheels / spokes. I actually see I'm cited in the phd he cites, quite a fun surprise!
This is a great article. It showcases lots of the "simple, but surprisingly advanced" things surrounding bicycles. Which was what got me hooked in the first place. The visualization of how you have to turn right to go left is excellent. I've mentioned that fact multiple times here on HN, it's not commonly known, you just "do it" when you bike! And it explains why you sometimes can feel the curb "sucking" you towards it when you try to avoid it: you unconsciously avoid turning the wheel towards it, but that actually makes it so that you're unable to actually steer away from it!
Veritasium did a great video on the opposite direction turning. They even show a bike that prevents you from turning the wheel one way to show that its essential.
When I took control theory at university, in the last lecture, the lecturer took out a bike with rear wheel steering and challenged us to ride it in the hallway outside the lecture hall in the break. No one could get it to roll more than a couple of meters. The second half of the lecture was spent proving that a rear wheel steered bike is in fact (almost) impossible to control.
But it turns out that it doesn't matter whether you place the thrusters high or low, stability-wise. What matters is that the center of mass is in front of the center of the center of pressure.
Aren't they just as stable as regular rockets, but it's very inconvenient to put the thrusters on top?
It's called pendulum rocket fallacy and from what I can tell that's the case.
Yes, it was pretty much a reverse bike with the saddle on the frame and a handle bar just behind where the seat post should be, connected to the steering axle. The details is a little bit fuzzy since it was a couple of years ago but iirc it is actually possible bike backwards at slow speeds but require a lot more active balancing from the rider, and at some point it becomes impossible as the speed increases. Also it concerned the case where the bike is riding straight ahead, it is possible that it is easier to control if riding in a curve.
The term used in motorcycling is countersteering. A lot of people think they are using their body to change direction but that would not be sufficient. Also it helps to be deliberate about the handlebar pushing motion for safety and performance.
A fair bit of the stability of a bicycle (especially at low speeds) is due to the fact that you have a human holding onto a bar that behaves exactly like a thing that a human would grab onto to steady themselves. If you grab this bar and rotate it clockwise, then you yourself will rotate anticlockwise - and that is true whether the bar is the handlebars on a bike or a random bar fixed on a wall. Holding ourselves steady by grabbing onto something is something that humans have a remarkably effective and quick feedback loop for, which is why bicycle riding comes naturally once you get over the fear of falling off and just do what feels right.
Rigging the handlebars to turn the wheel the other way cancels out that automatic feedback loop.
> ..you sometimes can feel the curb "sucking" you towards it when you try to avoid it
I was shopping for a kids carrying bikes, called bakfiets[1] (I think) in the Netherlands. The salesperson offered me a trial ride, his advice is something I still remember. Don't bother about the front wheels (they are far out in front), just look where you want to go and your hands will take care of steering and balancing.
Target fixation - you'll go where you look, for better or worse. Inexperienced riders will often stare right at the obstacle they're trying to avoid and ride right into it.
I'm sure the poster meant it was their first time riding a bakfiets, not that they never rode a bike before. The length of the bakfiets makes it a bit of a challenge.
The counterintuitive turn is more pronounced in motorcycles. You are literally pushing against the turn as you lean into the turn, and to lean in you have to turn out. Even more pronounced in sport motorcycles. Maintaining the centre of gravity during a lean at those speeds is a lot of fun to master. It’s one of those heart racing moments, literally no room for error.
Indeed, if you want to make fast turns at speed on a motorbike the trick is to first push/pull the bars in the oppositive direction - that gets the bike leaning over and then the bars come back and take the natural position for the turn. It's amazing how quickly even a big, heavy bike (e.g. BMW tourer) willl lean over with the right technique. At very highspeeds it takes quite a bit of muscle too.
I took the Motorcycle Safety Foundation basic course a very long time ago. One of the instructors brought his Honda Goldwing to the course just to help us get over the fear of falling over by showing that even a massive heavy motorcycle could go through all the tight turns without any problem.
I have to say, that course was some of the most fun I've ever had!
One of the best decisions in my life was to take this course. I started riding a Buell after this and boy what a thrill it was to lean this bike in the Pacific Northwest hilly roads.
Yes. On a motorcycle at high speed you have to actively maintain force on the wheel towards the outside of the turn to keep in the turn. If you stop the bike will straighten up.
Unicycles have a similar counter-intuitive control method where you need to accelerate the wheel to slow down and vice versa. Turning doesn't work quite the same way though as you can do sharp turns by twisting your hips and thus changing the direction that the wheel is pointing.
Never thought about, but yeah I guess it makes sense. If you were to suddenly stop you would be jolted forward, so need to get a bit behind the wheel first.
Many times I've observed myself as closely as I can taking a turn. I can't observe any steering in the opposite direction. I start by leaning, then turn into it (if I turn the wheel at all, which I don't unless the turn is very sharp). Maybe I really do steer the other way some imperceptible yet vital amount? This summer I plan to weld a bicycle unsteerable and see what happens when I try to steer solely by leaning as it feels like I generally do.
The welding the bars experiment you are talking about is done in a motorcycle school I once took with Kieth Code (California Superbike School), in order to prove to riders that countersteering is real.
I held an American Pro Superbike racing license in my 20s and countersteering is the only way I ever steered. Here is an experiment - go into a flat and wide open space like a parking lot, ride straight, and then turn to the right hard while keeping straight up and down. Hold the pressure to the right and I promise you will turn left or will initiate a turn to the left. The harder you turn the bars right the quicker the bike will fall left and begin arcing left.
In chicanes on a circuit track you can flip the bike over from one side to the other extremely quickly doing this. I've done this on everything from mountain bike to superbike, the latter being a more pronounced effect.
The only time I don't countersteer is when doing a 180-ish degree turn on a dirtbike, like what is common on an SX course. Also, when doing an extremely slow turn on a sport motorcycle, like what's common in USA motorcycle safety courses. But when moving at speed I always countersteer.
Knowing this phenomenon and using it may save your life.
Countersteering helps initiate that lean more quickly than just organic falling over. It's possible you're exceptionally patient but it's also possible you're just countersteering a little bit to initiative the lean, without noticing it.
Interestingly, I read about this a long time ago and intentionally turn the handlebars the wrong way to initiate the lean. (Not because it's necessary, but because it's weird. Riding your bike can be boring at times.) Very smooth.
It's totally necessary to push the handlebars in the opposite direction to initiate the turn because bikes are not minimal phase systems (at least that's what i remember from control systems).
I've watched it multiple times and I'm not entirely convinced I don't tend to turn in some different way from the average person. One person managed the turn correctly by accident in the video because they'd happened to lean the right way beforehand.
It's easy to see countersteering in action if you have a quiet damp road. Try riding in a straight line and then turning to the right. Then dismount, walk back to where you started your turn, and have a look at your tyre tracks.
How thick are your tires? Initiating the turn requires just the tiniest bit of countersteer on very thin tires, in my unstudied experience. I did the same experiment as you and found it was so subtle as to be basically unnoticeable.
Yeah on a motorcycle leaning doesn’t do anything to engage a turn. “Push the direction you want to go” is what’s drilled into you and also just feels natural.
I can at least confirm that my daughter was very much surprised when her balance bike [0], which is essentially a small draisine, stayed upright when she lifted her legs.
Similar concept that gets a lot of people in trouble on the OneWheel, "lean forward to slow down". When you're going to fast, the you intuitively lean back, which actually accelerates. There's even been a handful of lawsuits around this physics issue.
But why can't the inability to make a sharp turn be explained by the need to arrest forward momentum? The momentum has to change direction. Turning 90 degrees causes sudden loss in velocity. Turning against the arc of the turn i.e. along the orbit of the turn transfers the forward momentum into angular momentum. Thus, a counterturn is just an efficient way for the bike to follow the arc.
Gyroscopic forces are fun. That phenomenon kicks in around 20-25 mph but that’s when I was on a crotch rocket. I’ve experienced it at like 15 mph on a bicycle.
It was mainly a CS thesis on multi-objective optimization algorithms, and wheels were my chosen application. So me not being a mechanical engineer I didn't exactly push that side of the science any forward.
But my algorithm did end up "inventing" the 3x pattern perfectly, which I think was cool. Both as a confirmation that it's really a good versatile pattern being pareto optimal in multiple objectives, and the algorithm finding it also verified that my approach did have some merit.
I have a conceptual wheel design idea that I feel that only you can accomplish a successful design...
Before I email you some rambling wall of text, would you be open to hearing about some crazy concepts?
--
TL;DR:
The idea is to use Toroidal Propellers as 'spokes' in various light-weight, 3d-printable 'turbines', along with wind-shrouds to force vector air current to dynamos... specifically in various scaled applications for objects which already have a rotational input (shaft, wheel, spinny thing, etc)
Open to hearing from the loony bin?
Where read thesis?
Also, I am Norwegian! (but from Ballard, Seattle)
---
People tend to think of 'scaled' as in "LARGER" -- but it can also be used to refer to smaller...
Think of toroidal pumps in tiny bio tubes (veins, maybe, distributed heart pumping/nutrients pumping to isolated bio-assets (simulate pumping of heart of external bio-fluids to individually separated muscles connected to a biovascular pump system that can mimic the actual heart pattern of a donor to keep tissue happy) perhaps?)
Anyway -- its the evolution of Davinci's first documenting the importance of eddies, which we later discovered is how pumps work... (We knew pumps, but we didnt understand how they worked (documentedly) in Archemedies time (we also 'know' he did "discover" this, he documented it...) Anyway... (Sorry for the rant)
I want to develop a way to capture the eddies around certain objects.... If we examine Whales (the animal) they have a symbiotic relationship with barnacles... the barnacles attach to the leading edge of their fins. Whales eat off of plankton, small critters...
The barnacles create eddies along the wing surface..
BLAH BLAH BLAH
And the eddies feed both.... And I would like to talk to you about how this impacts flight! (passive extendable props that are fed off eddy wash) and pumps, and fluidic dynamics... and a bunch of cool boring shit.
The “kerb sucks you in” phenomenon is target fixation, you’re getting closer to the kerb because you’re staring at it. It’s a common cause of motorbike accidents, among other things.
You often see these two concepts (target fixation and counter-steer) discussed in threads on steering.
Not denying that target fixation is real and operative in some circumstances ... but counter-steer is even more "basic" in that it is solely a function of two-wheel dynamics, not rider psychology. You really do need to steer slightly right in order to initiate a turn to go left.
> Little I knew this is actually a test that psychologists use to demonstrate how our brain sometimes tricks us into thinking we know something even though we don’t.
> I collected hundreds of drawings, building up a collection that I think is very precious. There is an incredible diversity of new typologies emerging from these crowd-sourced and technically error-driven drawings. A single designer could not invent so many new bike designs in 100 lifetimes and this is why I look at this collection in such awe.
> how our brain sometimes tricks us into thinking we know something even though we don’t
The way I try to avoid this is to remind myself that knowing the name of something is not knowing about something, only about the existence of that something.
There are lots of things I know the names of, but relatively few things I actually know about.
The classic example is asking people to describe the process that causes the phases of the moon. Most (myself included the first time) describe an eclipse, which is wrong.
I was just talking to a friend about moon phases the other day, saying that I'd never really understood why it does what it does, only that vaguely things rotate around each other and this waves hands does things.
He explained it like this which really helped: you can choose all sorts of frames of reference when you think about this stuff, so choose one where the sun and earth are stationary compared to each other, and then only the moon is rotating - less stuff to think about!
Now you've got the earth spinning very fast in the middle, the sun sitting off to one side, and the moon then goes in a slow circle around the earth. If it's on the opposite side of the earth to the sun, then it's going to be fully lit up, but it's also only going to be visible at night. If it's on the same side as the sun, then the side that's facing us is going to be dark and difficult to see, but it will be in the sky during the day, which is why occasionally the moon is visible in daytime, even though we all know the moon comes out at night.
I think that idea of changing your perspective - in this case, literally, by changing the frame of reference - is really helpful when it comes to understanding things that we only know about. Like, I've known about the solar system since I was a kid, I've seen all of the models, I surely made my own as a schoolchild - the knowledge is all there! But for understanding, I needed to find a new perspective.
That's probably true of the bike thing as well, thinking about it. Knowledge of a bike is easy: it's two wheels, handlebars, a seat, and pedals. But understanding how a bike is made requires thinking about the frame, and that's just a squashed parallelogram with a stick coming out of it. Once you visualise that, it becomes really obvious how the rest of the bike gets put together, but the frame is necessary for understanding. Otherwise, you just put together the things you know about and then have to draw awkward lines in between to connect them.
> He explained it like this which really helped: you can choose all sorts of frames of reference when you think about this stuff, so choose one where the sun and earth are stationary compared to each other, and then only the moon is rotating - less stuff to think about!
Even easier: choose one where the sun and moon are stationary, and place the Earth somewhere near the moon. The side of the moon facing the sun will always be fully brightly lit, and the proportion of that which is seen from the Earth is based on where we place the Earth.
Of course the Earth doesn't orbit around the moon, but for the purposes of this model it's irrelevant.
I would explain it like this: take a tennisball and shine a flashlight on it from one side. Make sure you do not see the origin of the light by holding it just right of your shoulder.
I 100% agree with your comment however in regards to it's relationship to the parent comment I have to disagree somewhat in the usual nitpicky hackernews fashion:
Asking someone to draw "a bicycle" is different to asking them to draw a specific bicycle or a functional bicycle. Also what does it mean to "know something"?
If you ask someone to draw a house and they draw a square with an overhanging equilateral triangle centred on top, it's not that they don't know what a house is. That's just a symbol representation of their own personal definition of a house.
The equivalent here would be if you drew that same stick-figure house but put the door adjacent to the roof rather than the floor, or the triangular roof along one side rather than opposite the ground.
This happens to me alot. Motivated by curiosity I will make the effort to acquire a piece of knowledge but since I don't have a functional use for such knowledge parts of it slip out of memory..
..then some time after I will have a functional need for the knowledge I learnt previously but relearning something that is already somewhat familiar isn't that captivating so it ends up being a struggle the second time.
What a great example! As a recent astronomy enthusiast, I found myself doubting this comment initially ("well, eclipses ARE related"), and this despite the fact that I have a toy tellurion right by my desk.
But hearing a particular phrase in the below video helped correct my model. One sanity check is that you can see non-full moons during the day (although I definitely would have just assumed it was still a matter of angles).
Side comment: This is the first time I've seen my preferred username used for its actually meaning. And I've been using it for almost 3 decades. Neat.
I was going to use tellurian, which means an inhabitant of the earth, then saw that tellurion was sometimes used as an alternate spelling in an old Webster's dictionary I was looking through, and preferred it.
And yes, I did search through a dictionary to find a username.
> The classic example is asking people to describe the process that causes the phases of the moon. Most (myself included the first time) describe an eclipse, which is wrong.
To me, a neat consequence of this is that if you know what part of the cycle the moon is in, you know where it will be relative to the sun in the sky (and vice versa).
The trouble with the very first render is that the author is wrong about why the bike wouldn't work. The head tube isn't braced well enough to allow the front brake to be used, and would twist when cornering to a degree that would unsettle most riders. The missing chainstay would only be an issue for powerful cyclists or people standing up to pedal. But the bicycle shown could definitely be built and ridden. Probably more practical than Saul Griffith's plexiglass bicycle (that was also built and ridden).
At one stage Klein had a problem with the chainstays separating at the bottom bracket and a number of people rode those bikes after breaking them... almost exactly the "missing chainstay" problem above.
I've built some very weird bicycles and broken both those and conventional bicycles. I have at least some idea of what works... I'd be willing to build as many of those renders as someone was willing to pay for.
A missing top tube is much easier to deal with than a missing down tube. Lots of bikes have pushed that a very long way. But the main forces there are twisting the pedals against the handlebars and using the front brake, which the downtube is very involved with.
You could build that bike out of steel tubing and it would be rideable, as I said, but insofar as it's broken it's broken at the missing down tube.
Slingshot, for example, had no down tube just a wire and that was a bit notorious for being squirrely in the steering.
You could definitely build a bike like that that was quite rigid, it would just be heavy or expensive or both. A decent carbon layup, for example, might bring it back to the chain forces going through the seatstays being the main issue. But that's something you'd want to analyse a lot before building it. And I think you'd end up wanting a much bigger head tube lug than shown.
I didn't collect photos of the real experiments, those were mostly "grab a scrap bike, hack it about, (try to) ride it, bin it and try again. But if you wander the mozbike site there's a few of those. https://moz.geek.nz/mozbike/see/misc/2001/index.html has the "MBB FWD recumbent" that's just a cheap chair welded to a BMX frame :)
this was one of the greatest installations i've ever seen in an art gallery. You have no idea what you're looking at until you've passed through all the rooms...seeing a real life "fucked up" bike in the last room...is a little mind blowing haha
The most important fact is that riding a bicycle is 3 to 5 times more energy efficient than walking. Depending on the road, bicycle, terrain and weight of the rider. Riding a bicycle is the most efficient self-powered means of transportation.
It's no coincidence that other human-powered transport mechanisms (aircraft, boats, etc.) commonly use pedals for the drivetrain. It's a lightweight way to use the body's strongest muscles, especially when high power is critical.
I wouldn't say it's common at all in boats. The two main human-powered boats are canoes and kayaks, and both use the arms, not the legs. There's also rowboats, which again use the arms. Pedal-powered kayaks do exist, but are rare.
It would make more sense to use the legs, but it's a much bigger engineering challenge than making a simple paddle and a boat that floats with no holes in the bottom.
That's certainly true--oars are by far the most common configuration for human powered boats. I was thinking more about human powered boats that set speed records, e.g. the Decavitator
As a rower myself I wanted to type the same correction initially, but then realized that the parent comment is probably referring to a rowboat rather than a racing shell. No sliding seat, no leg drive.
I had a look and the source cited for it being the most efficent self-powered means of transportation is from March 1973; I wonder if there's been any new developments since then.
Random things off the top of my head: Some time ago they built a self-propelled helicopter, which also used bike technology (gears etc). I vaguely recall that people did state that rowing is what you should use to get the most energy out of a human body - it is (or can be) a full-body motion, including the large muscles in the back and legs and the smaller ones in the arms, while cycling mainly uses the legs. But the mechanism to translate rowing energy into the propellers was too heavy, or something like that.
Actually it might have been a HN thread. Here's one from 10 years ago, and it just so happens that I had made my account by then so this was probably it: https://news.ycombinator.com/item?id=6028326
I read somewhere (lost to the fickle beasts of memory and time, of course) that rowing and the like is not particularly effective, precisely because it requires big, slow movements against resistance, which the human body is not that efficient at[1]. What we are efficient at is quick, light, repetitive movements – like pedaling with the proper gear selected. This is why Ivan Illich phrased it as the bicycle being "the perfect transducer to match man's metabolic energy to the impedance of locomotion".
[1]: This is also why rowing and weightlifting are such a good type of exercise to get stronger, and why bicycling requires that you put in a lot of hours to get stronger from it.
> I vaguely recall that people did state that rowing is what you should use to get the most energy out of a human body
The limit for athletes is normally cardiovascular, commonly oxygen - VO2max the the measurement there. For less fit people it can be the cardio side, their heart just isn't up to it so their muscles fail and they lie on the ground twitching. Oxygen-deprived people pant and gasp.
So recruiting more muscle groups really doesn't help. What does is increasing oxygen intake, and this is where recumbent bikes come in. The laid back position opens the thorax and increases effective lung capacity. As well as reducing air resistance, except that that's a very subtle thing that mostly depends on the rules governing the sport in question (fairing on bike and kayak, for example, are variously restricted or banned in most relevant sports).
You can also reverse that and exercise at high altitude... less oxygen for everyone!
> So recruiting more muscle groups really doesn't help. What does is increasing oxygen intake, and this is where recumbent bikes come in. The laid back position opens the thorax and increases effective lung capacity. As well as reducing air resistance, except that that's a very subtle thing that mostly depends on the rules governing the sport in question (fairing on bike and kayak, for example, are variously restricted or banned in most relevant sports).
Recumbent riders generally have much lower peak power and ftp but higher sustained so VO2 differences wouldn't explain it. The main attribution I've seen is aero and marginally less muscle power used for motions that aren't related to pedalling.
My limited experience is that it's easier to recruit more muscles on an upright, so your peak power can be higher. In my 30's I would hit double for a 30s trial on an upright vs a recumbent (last time I had a decent power meter was in my 30's). But over 5 minutes the recumbent was better even if both were fixed to stands. So I don't think it's the balance issue.
For an hour or more the recumbent wins just for comfort, and unfaired records it wins on air resistance (that's why the UCI banned them, it let povo scum beat gentlemen athletes). But then the UCI doesn't have faired records... it's only the IHPVA et al that make that distinction.
Interestingly the PBP etc records (we don't have records, this isn't a race!) are all uprights AFAIK. But that's xenophobia rather than technical skill from what I know. And the Round Australia record is an upright, largely because no-one on a recumbent has been inclined to attempt it. RAAM is held by a bent (https://en.wikipedia.org/wiki/Race_Across_America#Records).
Recumbents are notoriously difficult to ride as the grades get steeper. Upright cyclists have the advantage using different body positions (i.e. standing), but 'bent cyclists can't do that. On the steepest grades, it can be a challenge to even keep a 'bent's front wheel on the ground.
If we take distance passed as a measurement, intuition tells me that bicycle is more efficient, since it doesn't have to lift the whole body, just move it around on wheels which provide very small friction.
Perhaps if we had bicycles with comfortable seats we can recline in, we could save up energy needed to balance our body on a bicycle. Something like a pedal boat, but with wheels.
Recumbent bikes definitely are more efficient due to aerodynamics if nothing else. I suspect being able to push back against the seat helps too, though.
This is true - the ergonomics as well as the aerodynamics are a step up. I would like to note though a disadvantage in ergonomics when it comes to hills, which nicely illustrates another feature - often unacknowledged - of conventional frames.
I live on a hill and commute on a conventional/non-recumbent bike. There used to be a bearded white middle-aged guy living half way up our hill with a recumbent and I noticed the recumbent seemed way /less/ efficient on our hill climb. A secondary design feature for conventional bike geometry is how well it works on a hill when you stand up. There’s something about how you can use your weight, pulling on the handle bars at the same time as rocking the bike frame side to side, to maximise downforce on the pedals, that just works incredibly well for propelling yourself and the bike up a hill. None of that is available on the recumbent designs I’ve seen, and because the hill slows everything down, they get less aerodynamic advantage too. So while they’re great on the flat, I think a key limiting factor for recumbents may be that they’re not so good in hilly places.
Ran into a fellow touring once with a recumbent and a trailer for his dog! All told, a 250lbs rig, few would be able to celebrate as much getting to the top of santiam pass in oregon (approx 4000 ft climb)!
I've seen a few of them in the city. The seem great, but I wonder how well they steer. They're low to the ground and seem less visible (I've seen them with flags). On a bike your center of gravity isn't much higher than walking, and you can put your feet out quickly and essentially be in a standing position .
They steer well enough for bike trails. Longer (e.g. tandem) ones may have some challenges with tighter turns (need to do a 90° adjustment at a light).
Flags are common for recumbent for visibility.
The lower center of gravity and the "it's real hard to fall off" can make it useful for people that have difficulty with balance. The back seat of a tandem is suitable for someone with needs for additional assistance ( https://www.terratrike.com/product-category/accessories/assi... ) - my mother would go tandem with one of her friends who was legally blind and needed to use a walker.
I bike A LOT -- >1,000 a month on a 29" full suspension e-bike (Orbea Rise)
But I have been biking daily for morethan a decade, and was a daily bike commuter in the bay area for ~15 years....
I see many recumbent bike a day when on the trail. At least >5 a day.
My house backs up to the American River trail, I literally leave my house and get directly onto the trail in less than 2 mintues.
Recumbents are all over the ART in the Sacramento Area.
One thing I have noticed though, and this is just a statistical observation on my part biking that trail regularly for ~2 years...
The average Recumbentist is a White Male, Typically with a beard >50 years old, 30% are overweigth, 30% are average build, 30% look semi/more-fit, 10% are female.
They look fun though. I'd love a long distance camping -e-bike version of one with a trailer and a detachable, light, curved windscreen that can be put on the top of the trailer when one wants.
> The average Recumbentist is a White Male, Typically with a beard >50 years old, 30% are overweigth, 30% are average build, 30% look semi/more-fit, 10% are female.
Recumbents also used to be far more expensive than standard bicycles (although now there's a lot of expensive standard bicycles) so an older demographic isn't surprising.
Recumbents are also lower in height and a lot easier on people's joints so are particularly good for people who have medical issues or mobility impairments. So, again, your demographics aren't surprising.
> They look fun though. I'd love a long distance camping -e-bike version of one with a trailer and a detachable, light, curved windscreen that can be put on the top of the trailer when one wants.
> The average Recumbentist is a White Male, Typically with a beard >50 years old, 30% are overweigth, 30% are average build, 30% look semi/more-fit, 10% are female.
I'm white, male, beardless, and 40 and am almost always the youngest when showing up at a recumbent meetup.
A lot of the current crop of recumbent riders (in the US at least) got into it in the late 90s and early 2000s. As the boomer cohort aged out of riding two wheeled recumbents there was a significant drop in demand for recumbent bicycles and a corresponding increase in recumbent tricycle demand. The companies making fast/racing recumbents stopped due to lack of demand (basically just Performer and Bacchetta are left) so there aren't a lot of us left in the fast recumbent bicycle crowd and almost everybody is running a 10+ year old bicycle. I have a 2009 Optima Baron, for example. More casual recumbent bicycles like LWBs or crank forwards are still around and seem to be more popular in the midwest than on the coasts. I live in NYC and recumbents are particularly rare here due to the downsides of recumbents in the city, mostly sight lines in traffic. I've seen 6 in the wild in the last 8 years and I usually see 4 or 5 recumbent trikes on mass rides like the 5 Boro but all the trikes have been from out of town.
The main losses are drag and, at low speeds, friction.
A velomobile (enclosed bicycle or tricycle where you lie back) mostly solves the former. The effort of a light walk moves you at about 30km/h on the flat (but slightly slower than walking on a steep uphill).
Steel rails would make it slightly more efficient again.
As I understand it, reducing unsprung weight (which is not very much for a bicycle with no suspension beyond the tires) can have an outsized effect, but actually reducing weight mostly matters for ascending. For non-competitive cycling, other factors seem like they should be much more significant.
A big one, which is banned in most competitive formats, is a fairing. This is much more effective than having a human hunker down and try to be aerodynamic. Even for an upright cargo bike (which is generally extremely heavy), a fairing in front can make a dramatic difference on level ground with no wind.
Which is great if one is racing but not so much for long distance riding or riding for the joy of it. Most riders are not racing at any level where it makes a difference. A well made steel frame is a joy to ride. They are incredibly comfortable and track exceptionally well, unlike stiff frames.
carbon fiber is a lot less efficient regarding manufacturing though, compared to aluminum. The difference is even bigger with respect to steel or the life time of the materials
The difference between riding on grass and riding on a dirt trail is VAST - grass is like 3x worse; but when that dirt trail turns into a mud trail, the grass is better.
Humans made trails by walking for eons before roads were envisioned. Maybe for a chariot you need a proper road, but a human made trail is just fine for a bicycle.
I rode my mountain bike A TON as a kid, gave it up for the more "prestigious" road cycling as an adult, but maybe 2 years ago bought a mountain bike to ride with my kids.
My goodness it took about five minutes on a local trail to feel like that same little kid I was back in the day, the feeling of speed, focus, and flow. There's nothing really like it for me, as it puts me square in the moment.
Denmark doesn't have hills. It might have "hills", but not real ones. The same goes for the inhabited parts of Sweden.
Colombia could have been a better example, they have real mountains and people over there do use bicycles to do their thing. Granted, not a great percentage of the population does it because you do need to be really fit in order to handle 10% slopes, but of those that do you might get future Tour de France winners.
Yeah, I was thinking at Bernal when writing my comment. As far as I know he used to bike to school when he was a kid, and he wasn't living in the flat areas of Colombia.
I think it is closer to 9-10 times (on level asphalt road on a "normal" bike) although it heavily depends on some factors like speed, type of bike and your proficiency, terrain and type of ground.
Riding a bike is most efficient at a certain speed and becomes less efficient very quickly as you get faster. So when I mean 9-10 times more efficient, I mean a person walking at a comfortable speed vs cyclist riding at a comfortable speed (on relatively level asphalt road).
"studied" is a strong word. he read an article once and then talked about it for the rest of his life because it suited his pitch. i doubt he cared about the scientific veracity
Not sure if this is common knowledge by now, but one of the mind blowing things about this blogger is he writes these WebGL interactions, seemingly by hand, no framework. Like, best I can tell, keying in the vertices. See https://ciechanow.ski/js/bicycle.js
I'm always in awe of everything he produces. I read somewhere that he uses helper scripts to generate some code, but it's still all manual labor. It's breathtaking.
Bikes benefit a lot from pneumatic tyres, pressure pumps, smooth asphalt (not cobbles), precision engineering of chains, chemistry of oils and lubricants, rust-proof steel, rubber brake pads with compounds that last long enough and resist rain, spring steel for suspension, cables that don't stretch. Without those things you get a wooden boneshaker hobby-horse, large, heavy, energy inefficient, incovenient: https://duckduckgo.com/?q=hobby+horse+victorian+bike&t=ffab&...
(And internal combustion engines; how are you going to distribute them around the Roman Empire by the tens of millions without trucks or ships?)
And now of course some of the most prestigious races in the professional cycling world are across predominantly cobbled roads as a form of torture for those racing.
To expand on one of those things - bike chains get slightly longer as they wear out. Once it's about 1% longer than it started, it looks about the same as it always did, but it's starting to damage the drivechain and you need to replace it. An ancient Roman blacksmith has no hope of making a chain with anything like that level of precision.
I believe you only have this problem if your bike has gears based on a set of sprockets (different size chainwheels and a derailleur to move the chain from one to the other).
In Europe (Holland in particular), people ride single gear city bikes (or internally geared hubs) for decades without replacing chains or cogs. When you only have one chainring and one cog, they wear along with the chain, and it takes a very very long time to encounter problems.
It's when you have the sprocket cluster with multiple cogs that are not all wearing equally, that you get problems. Or often the problem on geared bikes doesn't appear until you replace your worn chain and the new chain no longer meshes well with the cogs worn to match the old chain.
Nope, with single speed/hub gears chain wear is still a problem, it's just that they're less sensitive to it and there's fewer parts to replace. When the chain gets longer it gets loose, but it has to be very loose indeed to fall off or skip on a single speed. With a derailleur setup there's a tension arm with a weak spring so when the chain wants to skip that tension arm lets it. Derailleur setups commonly have some cogs with fewer teeth than single speeds so the problem is more obvious. Also, often derailleur cogs are aluminium while single speed ones are steel (not always!).
Typically a safety bike will get through 3-5 chains before needing to replace the rear cog, and many more before replacing the chainring(s). But Pinion gearboxes in the bottom bracket often run small chainrings that are similar in size to the rear cog, and I suspect they need to replace both rather than just the rear one.
I ride a bicycle with a hub gear as my main form of transport. About two years ago, I noticed the sprocket (rear cog) was getting very worn, so I removed it so I could reverse it and let it wear on the other side of the teeth (standard procedure for this sprocket to extend the wear life). But I accidentally put it back the same way as before and didn't notice until recently when I changed the hub oil. I had no problems with the chain skipping, despite the heavy sprocket wear (although it's now worn to the point that I no longer feel comfortable letting it wear on the other side of the teeth, so I'll have to buy a new sprocket). But you are correct that the chain wears more than the sprocket; I've already replaced the chain a few times.
Wouldn't the chain still need to be quite intricate and pretty hard to make even then? Though now that I think about it, you could probably make it in a way similar to chainmail, since tight tolerances aren't actually that crucial (the results would suck, but only compared to modern bikes). Though the other parts might be just as hard to make and especially to fit together (the bearings, the gearing for the chains...)
Bronze bushes work for bearings (still needs a lathe/ but not ball bearings). Chains can be belts of horsehair (or any civilisation with wire, tube and sheet metal can make a modern chain) or a treadle works okay. Spokes can be wooden.
The main limiting factor is probably the pnuematic tyre and smooth roads.
Chains don't stretch, they wear down. When measuring a chain, you measure the distance between links to see how much material has worn away. The links don't actually get longer from stretching.
You don't have to use chains though, you can have pedals on the front wheel, like the original bikes(velocipedes), or not pedal at all, just push yourself on the ground (balance bicycles)
Penny farthing bikes are death traps. Bikes that have similarly sized wheels with pedals on the front wheel aren't practical enough to be better than walking. Bikes without pedals are also not practical.
They were both more efficient than walking. Humans will put up with death traps if it means more efficiency in transportation (just look at car fatalities). The only reason they didn't took off faster was the lack of roads. And by the time we had tarmac roads bikes already evolved to have chains and read drive.
Watch a kid on a balance bike and tell me how it's not practical, lol. A 4 year old can bike around a whole park in seconds.
The key invention that made them possible was ball bearings. This is why the modern bicycle and the modern car were invented within a year or two of each other.
Yeah. Surfing is a great example of a Stone Age sport that has been radically changed by Space Age technology. Koa wood gets you a longboard that is hard to steer and can only surf long smooth waves. The modern surfboard is very much born out of California's aviation industry and its fixation on light, strong materials and aerodynamics. Surfing Pipeline is only possible with modern plastics, fins and shaping.
Well, I've got a bike from the 30s and it's perfectly fine for everyday riding. While I agree that most of those things you listed are valuable and convenient, good enough is often just good enough. Like I've got no use for any cables and I don't need precision engineered chains.
A parallel thought is that the first airplane is the product of bicycle mechanics and not railway or automotive mechanics.
As others pointed out, there are a lot of necessary technologies like rubber, bearings, lubricants, sprockets and chains that need to be developed, but there is also something very elegant about bicycles. If you start to mess around with a 70's era road bikes you get a sense of just how perfectly everything needs to fit together and how everything affects everything else. (You see it more clearly in older bikes because you need to deal with non-standard parts). I think I learned more about bicycles from the royal pain of a 1982 Peugeot than anything else. This is not to say that a car doesn't have similar complexity, but the use of chemical fuel and 4 wheels masks how the tunings fit together. With my current bike there is a serious difference when it is perfectly tuned.
Agreed. Bicycles are kind of a miracle of seeming simplicity hiding a ton of important developments of the industrial age. 99 Percent Invisible did a recent episode on just this topic: https://99percentinvisible.org/episode/the-safety-bicycle/.
The invention of the bicycle came at a similar time like engine driven vehicles. Before those became popular, the direct competitor for bicycles (one person transportation) were horses.
There might have literally not been a need to invent a bicycle as horses fulfilled the same purpose and had the advantage that they fared better on the back then nearly non-existent infrastructure.
Also: a single person transportation vehicle was not something a lot of people needed in their lives. You needed something to move stuff, but the demand to move single people daily came into existence with the dawn of big cities.
There's a reason that horses were the fancy sports car/military tool of the animal transport world. They eat a lot, break easily, and don't last long.
People used oxen, donkeys, llama etc way more than horses. And the Chinese invented wheelbarrows and used them extensively rather than using draft animals. They often use bicycles much the same way as wheelbarrows now, and rich people often find that amusing (possibly because a KMart bike is a toy, a Chinese bike is a workhorse).
The production of quality steel isnt thousands of years old.
Yeah they could produce small items - but to make the steel of the quality needed for bicycles is pretty new - the past 150-200 years with the Bessemer process
He settles on general economic and cultural factors. Experimentation requires there to be enough people with spare time and resources to play around with things with no immediately obvious payback.
Don't even get me started on airplanes though - there was only 66 years between the first airplane (Wright Flyer in 1903) and the moon landing (1969).
Disclaimer: that's of course a cool anecdote on the surface, but rockets have been around since the 13th century so they're two mostly different technologies.
Key development for flight: Wings which carry the plane. First planes didn't even have an engine (besides human)
Key development for rockets: Strong powerful engines to escape gravity. Aerodynamics matter relatively little, mostly for heat control.
I don't know how related the development of jet engines and rocket engines was. Of course things like the Space Shuttle, which has some airplane-like aerodynamic steering tie both together ...
We're playing a bit fast and loose with our phrasing here if we want to split hairs about the development of these technologies.
Powered, navigable, human flight existed before the development of wings.
The early rockets mentioned above weren't for human flight, nor for spaceflight. Rockets were developed to be terrestrial weapons, not to propel humans.
Rocket engines and turbine engines are both a type of jet engine. These engine technologies themselves weren't developed together because one was developed to make airplanes go higher and faster, and the other was developed to stab people with arrows better. If what we're really talking about is "human flight", then rockets and turbine engines were both used to propel humans on airplanes before anyone started considering spaceflight.
And then when humans did consider spaceflight, humans were developing space planes and tubular orbital rockets at the exact same time. The space shuttle was far from the first plane to operate at heights where the control surfaces no longer work. The X15 actually flew 2 years before Vostok 1.
The people developing human flight were always interested in going faster and higher. The technologies they experimented with were intermixed the whole time.
You will be amazed to know that the Ball Brothers, who invested the Mason Jar/Atlas Jar, and perfected canning and soups... is also Ball Aerospace - who makes super-high end space components for the MIC, black projects, skunkworks, NASA etc...
The safety bicycle (chain, pedals in the middle) is about a decade newer than the car (under 150 years), although they hit mass production within a year either side of each other depending in how you define it.
> Bikes seem like such a primitive technology, and yet as this article demonstrates, it takes a lot of engineering to design even primitive products.
Very strange. I get that we take things for granted if they've been around forever (ie. since before we were born). But I never considered bicycles "primitive". What makes you think that? Is it because they don't need electronics? What is a non-primitive transport technology?
Bicycles are a relatively new invention because they require roads/flat paths which are also a relatively new occurance, and came about due to the widepread use of horses and then carraiges for transportation.
A bike at any other point in human history would have been completely useless trying to traverse natural terrain.
Mountain bikes do not require roads or flat paths; they work fine on trails (hence the name "mountain bike"), which have existed since large animals evolved.
However, mountain bikes arguably require even more technologies than other bicycles, especially for suspension and brakes (MTBs pioneered the use of disc brakes on bicycles).
You probably know this...but the song is not about a literal bicycle...it's about Freddie being "bi". I only say this because it took me too long to realize that.
When I first started MTB in 2020... I tried to inflate my tubeless rear tire to 60psi once, because that was the "max pressure" written on the sidewall.
There are times you are incorrect, and wow, there are times you are very very wrong. They should make tubeless sealant in blood red just for fun.
Similarly, a Honda Fit with tires inflated to 90% ofthe sidewall's max pressure is /very/ fuel efficient, but you better plan on replacing tires pretty often. After a few potholes, usually.
What a phenomenal explanation of forces. I wish I had this when I took my first physics class in college. I thought it was particularly excellent at explaining "how much the wall knows to push back", which is something I didn't quite grok (but just accepted) back in college:
> You may wonder how the wall knows how much back-force to apply, so let’s look at the interaction between these two objects up close and in slow motion. As we apply the force, the box actually starts accelerating into to the wall, pushing its surface to the right:
> As the box moves to the right, it compresses the molecules in the wall, which create a spring-like force that pushes the box back. If that force is too small to balance the pushing force, the box will continue to move to the right, which compresses the wall even more, creating an even larger push-back force.
I wish physics teachers start using geometric product of vectors, instead of the cross product. This allows forces and torques to be combined into a single concept "Forque". Really, translations are just rotations around infinity and rotations are just composition of two reflections. If we allow the algebra to take care of rotations, physics becomes a lot simpler.
Wait until (all) teachers start using AND SHARING really well crafted prompts for teaching aides /r/coolguides lesson material.
There should be a central repo for all subjects where topics can be looked up to find a guide like this one - and the prompt is public, with revision edit logs (like wikipedia) such that a standard agreed upon response can be adopted by acedmia for explaining a particle concept.
Let the acedemics expand upon, tangent from, deep dive into the sub components of each topic.
Countersteering is convenient, but not required. A bicycle and rider are not a single rigid body. You can simply lean to one side and you'll have to steer in that direction to keep your bike under you -- no countersteer necessary.
I am not saying people don't countersteer, only that it isn't necessary to make a turn.
Also, bicycles aren't motorcycles where the weight ratio between rider and vehicle is swapped.
If you don't feel like clamping your handlebars so they only turn one direction, try this: coast along a straight line (and outdoor basketball court is great). Then pick a direction and just lean that way. You can absolutely keep your wheels on the line until you turn in the direction you picked, with no countersteering necessary.
This "fact" came about with a video of low skill riders who can't manipulate a bike very well, or don't know what it is they're doing when they do it.
He might be wrong, and just didn't know enough, but he is usually researching his videos very well and I would be surprised for him to be wrong about this.
What he demonstrated first of all is that you simply can't ride a bike that prevents the steer from turning in one direction. A bike continously falls to one side or the other, which gets corrected by steering in that direction to put the contact area back under the center of mass. This happens not necessarily through the rider's (conscious) action, even a bike with no rider does it to some extent, but in all cases it requires the ability to turn the wheel assembly freely around the steering axis.
IMO that means the bike in the video demonstrates failure to keep basic balance even before it gets a chance to demonstrate failure to turn properly.
just try it. roll perfectly straight and lean to a side. It accomplishes the same thing as countersteering, which is to put weight on one side of the bike, so when you turn that direction, the bike gets under you and you don't fall.
That's literally what they did in the video, I recommend you watch it. The issue is: you think you can just lean on the side you want, but you can't without counter-steering, so they devised a bike that literally does not allow counter-steering: you can't take a turn at all.
Because of the geometry of the front fork (rake and trail), if you lean to one side the bars will initially turn in the opposite direction. It's still countersteering. If you ever ride a bike where this geometry is wrong, which is difficult because it's so necessary, it's very different to ride, and you'll struggle to ride it non-handed.
I'm not sure your line method proves much since the countersteer could be very subtle. However I think you're still right. Countersteer makes you start to fall faster, but it clearly isn't necessary to make you fall because you do that anyway!
No it's not necessary in the strictest sense of the word, but counter steering achieves higher turn speeds, offers better control and precision, requires far less physical effort, and works at nearly every speed. I can't think of many pragmatic reasons not to use counter steering outside of just screwing around for fun.
This effect has a big play on motorcycles. Riding a bicycle is considered prerequisite knowledge for learning to ride a motorcycle, largely because of this counter steering. One thing that is more pronounced on a motorcycle is that counter steering only occurs while the bike is moving at speed. As in, you only counter steer a motorcycle above ~10mph (higher for some motorcycles). It's really cool to think about how intuitive this switch is, almost everyone picks it up quickly and it becomes second nature.
Countersteering applies at all speeds, it's just that balance plays a bigger role at lower speeds. The wikipedia article on countersteering goes into this a little bit.
Ride a motorcycle for 5 minutes and you'll believe.
EDIT: To answer your question more directly, you are steering in one direction to initiate a lean in the opposite direction. E.g. if you are attempting to turn right, you first steer left which generates force in a left-sided contact patch in the front tire, which causes the bike to lean right. The bike then assumes a stable right lean angle (you have to do some work with your body, but the bike naturally wants to do this), and the front wheel comes back into alignment, and you are now turning right.
Yeah, but you quickly counteract with direct steering after you initiate the turn, so the overriding sensation is one of direct steering at low speeds, even through the physics is the same. This is what I think most people are referring to when they talk about high speed / low speed steering.
The debate is whether countersteering is something you have to consciously do by turning the steering column ("yaw"), or whether it's an automatic effect of pushing/leaning down on the side you want to turn toward ("roll").
"countersteering isn't real" because "steering isn't real", cycles at speed turn by leaning/rolling, not steering/yawing.
Countersteering and roll are not mutually exclusive. The countersteer generally happens when steering whether you think about it or not. If you know about countersteering, you can practice it to make emergency turns.
For roll, Leaning in the direction of the bike is actually a bad habit (but it'll be fine on most road turns)
It turns out you want to lean the bike, and lean/shift your body in the opposite direction. This keeps center of mass above the wheels.
For example, the pro motorcycle racers with their knee an inch off the ground,they're leaning their body weight away from the turn, away from the ground. Meanwhile their bikes are leaning crazy hard.
That style of leaning is important for fast descents, or switchbacks, particularly switchbacks. Eg: "MOUNTAIN BIKE TIPS: CORNERING WITH CONFIDENCE" (start at 1:45) https://youtu.be/GFKPtEzE4xw
If you need to quickly swerve out of the way of an obstacle you push hard on the handle and you will immediately initiate a turn (you could just as easily say that your are initiating a lean). It's also well understood that handle bar input allows you to increase / adjust the lean mid-corner. I ride and never knew there was a debate about this.
Sheldon Brown is a great resource for bike information - lots of no-nonsense advice and explanations though it is getting a bit out-of-date now since his death. A particular favourite of mine is his chain cleaning method: https://www.sheldonbrown.com/chainclean.html
That would be something I'd personally consider out-of-date with modern chains. Apparently that makes me a "Lazy, careless cyclist" as I would never use grease on a chain. Nor would I ever follow this insane method of cleaning a chain.
Guess I'd consider myself to be an efficient cyclist, which may be construed as "lazy" by some.
edit: reading onward, he claims "Serious cyclists, who value performance..". I wonder what he considers "performance", because it sure appears he didn't consider or measure drivetrain efficiency.
Knowing how much of a PITA even modern in-depth chain cleaning is with solvents... I can't read that article as anything but satire. Even with old roller designs, an overnight soak in paint thinner followed by an ethanol bath should get the whole thing close to bare metal. Maybe the disassembly is specific to getting roller grease applied properly, unlike how he mentions manufacturers just dip the chain in a homogeneous lubricant? I'm surprised Brown didn't advocate for chain waxing over using grease for performance and maintenance reasons.
I hadn't actually read the chain cleaning page before but I did read his page on chains, which to an extent is contradicting with his chain cleaning page:
"New chains come pre-lubricated with a grease-type lubricant which has been installed at the factory. This is an excellent lubricant, and has been made to permeate all of the internal interstices in the chain. The chain and this lubricant need to be warmed during application.
This factory lube is superior to any lube that you can apply after the fact -- well, unless...see below."
Hard for me to tell what is original content vs. new. It has been empirically demonstrated that factory lube and grease are considerably inferior when it comes to drivetrain efficiency (performance) compared to a wet lube, which is less efficient than either dry lube or wax (with or without additives).
I've waxed chains for a while in the past but stopped a couple years ago. I now do a "good enough" quick clean of a chain using an undiluted degreaser, rinse with water and a final rinse with isopropyl. The whole process takes 5 minutes and the chain is clean enough for new application. Not clean enough for waxing, you'd want to throw in a solvent before ethanol/isopropyl, but good enough for wet/dry lube. I've no science to back longevity of chains following above procedure, I generally swap between 2-3 chains during a season to keep wear reasonable and then start fresh in the fall before indoor.
Bicycles are truly beautiful machines. They are the most energy efficient form of transportation. You can travel pretty long distances with not that many calories.
Modern fat bikes will be more efficient than walking in the scrub desert where I live, in grasslands, in not too dense woodlands, on any kind of open dirt/sand.
I've done 100 mile MTB races, and while it's not as efficient as riding a flat smooth road on a road bike, it's probably still more efficient than walking.
Obviously at some point there's a line, where you can't ride a bike, but for most roads and trails, the bike is going to win.
I think that the comment I was responding to was about scenarios where are no human-created pathways, trails or roads. As I mentioned in some of these, modern fat (tire) bikes are still great; in others, it is true that walking would be the best choice (unless you're at the level of, say, Danny MacAskill).
But yeah, in some natural environments, with some kinds of bikes, you can beat walking. The Burning Man festival is a great example, but it is also a terrible place to live.
That's why in most cases, without smooth roads, bikes are not practical.
I think it's fair to point out that you should be referencing road bikes then when you say bikes are not practical. Advancements in tubeless technology, suspension, MTB groupsets with dinner plate low gears, derailleur clutches, and hubs/rims designed to take a beating while supporting wide tires can definitely make a bike more efficient than walking on most terrain.
- Fat bikes are more efficient than snowshoeing or breaking trail on XC skis.
- CX bikes are more efficient than walking in mud.
- Fatter tire gravel bikes are more efficient than hiking through sand.
- A bike with a 51T cog and 28T ring will be more efficient than hiking up steep grades until balance at low speed becomes an issue.
They don't require a flat and smooth surface, but do benefit from a road of some sort. How do you make a road? You ride on it over and over again. Ever seen a sheep track? Is that not natural?
A smooth and flat road, while not necessary, is better and does make things a lot more efficient. The same is true for any wheeled vehicle but cyclists appreciate it a lot more than motorists.
They are the pinnacle of personal transportation technology. Not aware of anything that comes close. I'm not sure how anyone can use a car, keep filling it with more and more fossil fuel and think "yeah, this is good technology".
Perhaps more carbon efficient, but 15x less energy efficient:
> Biking takes around 25 kcal/km [iii] above basal metabolism, which is equivalent to .11 MJ/km. A typical car in the US gets 25 mpg, or 9.5L/100 km, which is equivalent to 3.3 MJ/km. The Toyota Prius takes only 5 L/100km, or 1.7 MJ/km. So a typical car takes 30x more energy per kilometer than biking, and a Prius takes 15x more. This is what we expect given how much heavier cars are than bikes.
At equal diet, the bicycle always win. You don't eat significantly more meat because you are using a bicycle to move vs a total couch potato that would use a Prius and eat the same.
I disagree with this. On days I cycle 100km+ in a day I do eat vastly more than if I drive 100km and don't exercise.
The energy does have to come from somewhere. If you're only cycling 5km in a day the reason you don't notice the difference in food quantity is because the amount of energy used for that small amount of cycling does not really exceed the amount of energy your body uses in a day for everything else. When you're cycling 100km, it's a different story.
It's an interesting question, and in fact the conversion of food to mechanical energy isn't actually very carbon-efficient compared to electricity generation or even gasoline.
Cars are actually very efficient at what they do, it's just that what they do (hauling around a 1000kg metal box) is an inefficient way to transport a human, and that's where the inefficiency comes from.
If you fill up a large car with full occupancy and go on a long road trip, I'd venture to say it's carbon-wise likely to be more efficient than all of the occupants cycling, regardless of diet.
Part of the problem is that the former number is wildly variable depending on the type of food, the type of production and the amount of transportation to get it to where it is eaten.
Whereas oil-derived fuels are ... well, they vary but not as much. Certainly some food production models (e.g. alfalfa-raised cattle eating for meet thousands of miles from where they are raised) are truly horrible, and may indeed be worse than using fossil fuels.
That said, plant-centric, reasonably local food systems that don't use much in the way of synthetic fertilizer generate massively less carbon than any sort of oil production in terms of distance-travelled-per-unit-of-carbon.
Part of the problem is that people consider that the driver are some aliens that do not eat anything, or stay fit by just following a strict diet and without doing any exercise.
But the true reality is most people eat more, make reserves and a huge fraction of the population is either overweight or do physical activities in the purpose of burning those reserves and feel better. Mixing transportation with the later is quite efficient.
- 2000kcal from food = how much CO2 including all the energy needed to farm it?
If it's 2000kcal from beef, you're looking at about 72.88 kg [1]
If it's 2000kcal from fish, you're looking at about 15.21 kg [1]
If it's 2000kcal from brassicas, you're looking at about 6 kg [1]
- 35000kcal from gasoline emits how much CO2?
35000 kcal is 140440 kJ, which would consume about 4.36 liters of gasoline, which would be about 10 kg of CO2 emissions [2].
So the CO2 efficiency of a car isn't that much different, and falls somewhere in-between a biker on a fully meat and biker on a fully vegetable diet. Biking isn't vastly more efficient than a car, CO2-wise.
That said, a motorized bike is hellishly efficient, CO2-wise, and trumps almost everything else.
If you're going to do that, what about the CO2 (gasoline) emitted to collect the gasoline? Given you need oil to extract oil, it's still far, far, far less efficient.
It's miniscule compared to burning the gas, or the oil industry wouldn't exist, considering a lot of the oil extraction and refinement industry is powered by oil itself.
You could have also Googled that number instead of trying to make a comeback for the sake of it.
I used to be an elite racing cyclist, I know what it is to need fuel in a 200km bike race
Besides, riding at conversational slower pace only need a fraction of that energy. When I was commuting 75km a day myy food intake may be at worst marginally higher than a day off.
Correct, I wasn't trying to make a statement about specific diets, just that diet does make a huge difference in evaluating the carbon efficiency of cycling.
Not even close to true. I can ride 60-70 miles on reasonably hilly terrain on about 2000kcal. There’s no car that can come close to that. And that’s assuming drivers don’t eat (the McDonald’s wrappers I see by the side of the road proves that they do).
2000 kcal worth of food takes somewhere in the range of 6 kg (for vegetables) to 72 kg (for beef) of CO2 emissions to farm.
If you assume a gas car needs 35000 kcal to make the same journey it's about 10 kg of CO2 emissions.
You're making a kcal-to-kcal comparison, which is apples-to-oranges in terms of climate change. Climate change doesn't care about kcal, it's greenhouse gases like CO2 that do matter.
I know internet forum people are going to come back with a retort about how drivers also eat, but the fact is that cyclists do need to eat more than drivers to make the same journey, and the math puts the answer somewhere in the middle, you need to do the interpolation.
Your numbers are absolute nonsense. You excluded the CO2 to extract the oil and refine it into petrol/diesel. Nobody eats 2000kcal of beef: that's 6 whole burgers!
On top of that, your numbers assume that drivers don't eat, which is self-evidently not true!
This is miniscule compared to the amount emitted by burning it. It sort of has to be, or the industry wouldn't exist.
Congratulations, you're now deliberately fishing at the opposite and and nitpicking at the opposite end just to argue, at this point, when you could be looking at the entire pond.
Of course nobody eats 2000kcal of beef, I never said that. I was providing an extremum of all-brassica and all-beef so that you can interpolate somewhere between them, but evidently you're more interested in taking the endpoints and call it nonsense instead of doing the interpolation.
So go ahead and assume drivers eat. Bikers eat more. Again, do the interpolation. You get some data, you do the math, then argue. You will still find that it's within the same order of magnitude. CO2 from food production is a thing, and it's hugely variable depending on diet, that's the point.
> So go ahead and assume drivers eat. Bikers eat more.
Not that much more, and you're being disgustingly disingenuous by just grabbing the mid-point. To get 2000kcal, you're going to be eating more rice, potatoes and raw sugar i.e. carb-dense foods to fuel the ride. That's more like 2kg of CO2, so vastly below the 10kg of CO2.
I can safely exclude the beef, pork, etc. because that's food I'd eat "outside" of fuelling the ride. To spell it out for you: I won't eat more meat because I rode 65 miles, I'd eat more potatoes and cane sugar. Thus, that's what we measure in terms of excess CO2 produced vs just sitting on my couch.
Also, I'm being very generous to cars here. Most don't come close to achieving 65mpg, and certainly not on the route I measured with the steep climbs it involves.
> The further away that line is from the center of mass, the easier it is for the force to rotate the object. In the following demonstration, you can apply two forces of the same magnitude to two identical boxes. The only difference is the distance to the center of mass at which these forces act:
> When the distance between the force-line and the center of mass is large, the box spins faster as well. That distance doesn’t change the acceleration of the box to the right and both boxes move with the same linear speed. However, that distance affects the angular acceleration of a box – the longer that arm, the faster the box spins.
This does not make sense to me. If the two forces are truly of equal magnitude, then shouldn't the one that is in-line with the center of mass accelerate it faster, since 100% of the force is being converted to linear momentum, while the off-center force is being split between increasing linear momentum and rotational momentum?
This would appear to violate the conservation of energy.
First, there is no splitting between linear momentum and angular momentum per se. They have different units, you can't add them, and it makes no sense to say "this is 30% linear momentum and 70% angular momentum". But you can calculate how much energy is stored in linear motion and how much is stored in angular motion, and (at least at non-relativistic speeds), you can indeed add them. So you are on to something here.
But Newton's Laws don't lie. If you apply a force F, then a=m/F, and the fact that the object is spinning doesn't change the acceleration. Yet applying the force off-center does indeed seem to add more energy to the object: you're accelerating it just as much as if you applied the force on-center and you're also spinning it.
So how do you resolve this? A piece of general advice in physics (and math, and many other fields) is to state your assumptions and your questions precisely and unambiguously. The question is: if you apply an equal force to two objects of equal mass, and there are no other external forces involved, how can one accelerate faster? But just because the forces are equal doesn't mean that the work (energy applied) is the same. In fact:
W (work) = F (force) * d (distance)
Divide by a small unit of time:
P (power, which is work per unit time) = F * v (velocity, which is distance per unit time)
And that's the velocity of the point that receives the force. And if you look at the animation, you will see that the off-center force on the rotating box is applied to a (variable) spot on the box that is moving to the right. So the power needed to apply the force is larger, and more work is done.
(In fact, the excess velocity is ωr, so the excess power is Fωr = ωτ (angular velocity times torque), which is exactly the power needed to produce angular acceleration. So energy is conserved and all is well.)
I think in my head I was mixing up "force" and "power"; it's clear that with two cubes travelling linearly at the same velocity, the one that's also rapidly spinning has more energy.
That it can take varying amounts of energy to apply the same amount of force to the same object was the missing piece for me, since I was thinking of force as power.
It’s fairly easy to demonstrate this if you have a friend with a bicycle. Have someone on a bike stay still and hold the brakes, and press firmly on their back. It’s easy. Then have them bike at a slow jogging pace, run along with them, and try to apply the same force on their back. It will be hard work.
> This does not make sense to me. If the two forces are truly of equal magnitude, then shouldn't the one that is in-line with the center of mass accelerate it faster, since 100% of the force is being converted to linear momentum, while the off-center force is being split between increasing linear momentum and rotational momentum?
Forces don't "split" that way. 100% of the force goes into creating linear acceleration, and 100% of the force goes into creating torque.
> This would appear to violate the conservation of energy.
It's not. The off-center force does more work, putting more energy into rotation.
A much worse book on the science of bicycles is "The Third Policeman" from Flann O'Brien.
Some of its wisdom:
“The gross and net result of it is that people who spent most of their natural lives riding iron bicycles over the rocky roadsteads of this parish get their personalities mixed up with the personalities of their bicycle as a result of the interchanging of the atoms of each of them and you would be surprised at the number of people in these parts who are nearly half people and half bicycles...when a man lets things go so far that he is more than half a bicycle, you will not see him so much because he spends a lot of his time leaning with one elbow on walls or standing propped by one foot at kerbstones.”
All the posts on ciechanow.ski are mind-blowing. The graphics, the gradual process of explaining from simple fundamental concepts to the complete picture.
I was messing with GPT-4 and pasted the HN front page with a prompt. In the response, it mentioned "a creative visual explanation of bicycles". Based on just the text "Bicycle (ciechanow.ski)". It really had me going for a minute until I checked the archives at the site and saw similar articles from before it's training cutoff.
I asked it (with no context), 'What is "Bicycle (ciechanow.ski)" referring to?':
Response: "Bicycle (ciechanow.ski)" is referring to a blog post by Bartosz Ciechanowski, a software engineer and blogger. In this particular post, titled "Bicycle", he provides an interactive, in-depth explanation and visualization of the physics and mechanics behind the bicycle, covering topics such as steering, gyroscopic effects, trail, and more. The post aims to provide a comprehensive understanding of why bicycles are stable and how they function.
In a different response it volunteered the correct URL.
This is a really impressive article -- he went quite far into the physics of bikes and wheels and didn't say anything that I could point to as being wrong.
Also see the work of Jason Moore (referenced in that blog) for whom it seems modeling bicycle dynamics in open source scientific python has been a huge passion for him for more than ten years. I remember in the scientific python development in those days there were these guys from like the hubble optics correction division and like the asml metrology department and then this one weird bicycle guy lol.
I used to like thinking about things this way. When I first started using computers I started to question how it all worked. It started with high-level and vague questions like "how does an operating system work" and as I learnt more and more it went deeper and more specific until I eventually learnt how a transistor works. That was enough for me.
But as I've become older I'm less interested in it and more willing to accept things "just work". I'm pretty sure that no part of the bicycle was invented by thinking about it this way. This is kind of a reverse engineering exercise. The inventors of the bicycle just knew that if you sat on a moving wheel somehow you could balance. They knew that if you put something soft around the wheel it would feel smoother etc. Nobody was sitting there thinking about crates moving and suddenly thought, what if it was two wheels with a person on it?
I don't know. Maybe it's because I already knew all of this stuff too (I'm an avid cyclist who has studied Newtonian physics). But I found this one a bit exhausting.
This is the greatest explanation of two-wheeled vehicle dynamics I've ever seen. Anyone who rides a bicycle or motorcycle should read this whole thing!
I think I found a minor mistake. Close to the beginning, there is a paragraph "The further away that line is from the center of mass, the easier it is for the force to rotate the object. In the following demonstration, you can apply two forces of the same magnitude to two identical boxes. The only difference is the distance to the center of mass at which these forces act:". Below that is a simulation of two boxes.
If you apply the same force over the same amount of time to both boxes, the same amount of energy goes into both boxes. As one box is rotating faster, it has a higher rotational energy than the other box. As both systems (boxes) got identical amounts of energy this means, that the slower rotating box should move faster to the right because more energy goes into this movement. Becaus E_input has always to be the sum of E_forward and E_rotation. Am I wrong and why?
Beautifully illustrated and brilliantly explained.
Derek Muller (Veritasium) on YouTube has a related video diving into the mechanics of bicycle riding. It shows what happens if you prevent the rider from performing the countersteer before leaning into a turn [1].
There's a similar neat video, "Most People Don't Know How Bikes Work", where they fix the steering so the handlebars can only be turned left, and people then aren't able to turn left.
This is another awesome post, although it doesn't address the one thing about bicycles I can never remember - which of the pedals has a reverse-threaded attachment to the pedal crank arm, and what's the complete force-based explanation for this necessity?
I'm not even sure if the force responsible for this is friction-related, or torque related, or some combination of both (probably the latter). The force is transmitted to the chaindrive in an off-axis manner, but the pedal itself is further removed from the axis, so when you push down on the pedal axis that's ahead of the bottom bracket axis - one side will tighten clockwise from the pedal's perspective, and the other side will tighten anti-clockwise.
Wow I got it right after going through this post! That's a first, though I'm still not sure I got all the forces right.
I really wanted the article to close its opening statement that "There is something delightful about riding a bicycle", by closing with the initial simulation, but with the rider embedded in an infinite procedurally generated landscape of rolling green hills and small villages.
I've been having some trouble adjusting the tension in my spokes lately. It seems like no matter how much I try, I just can't seem to get it right. Does anyone have any tips or tricks they could share with me?
On a related note, I've been wondering about the differences between mountain bikes and road bikes. One thing I've noticed is that when you take a sharp turn on a mountain bike, you tend to move the bike away from your body. But on a road bike, you maintain that alignment with your body and the frame. It's fascinating how these small differences can have such a big impact on the way we ride.
What do you all think? Have you noticed any other differences between these two types of bikes? Let's chat and share our experiences!
I've never built or adjusted a wheel. My understanding its not for the faint of heart. The late husband of one my CS professors (Sheldon Brown) put together a solid bike resource on the web...
He has some hints on wheel adjustment (after describing building)
Yeah it's an art. Sometimes you true a wheel and it just works. Sometimes it's like you're stuck in some local minima and can't get out; The wheel is egg shaped, so you tighten the long sides, then it's round but suddenly the wheel is tilted instead, you fix it but now it's off center, you fix it but the tension is wrong, you fix it but now it's egg shaped again..
You offer a good description of adjusting a wheel that is tensioned beyond its natural limit. Sometimes the art is making an assessment of the rim and deciding the best set of trade-offs given the rim's limitations.
> One thing I've noticed is that when you take a sharp turn on a mountain bike, you tend to move the bike away from your body. But on a road bike, you maintain that alignment with your body and the frame.
I don't know the answer but will toss out a guess.
I'd speculate one of the biggest differences is how each bike is used and its intended design based on that use case. Centrifugal forces combined with traction of tire to surface will be very different between road bike tires at high speed on pavement versus mountain bike tire and low/moderate speeds on dirt. Beyond that, a mountain bike is often rode through technical terrain that requires dynamic balance by the rider (rider strategically shifts weight over bike) - whereas road bikes appear to be rode with a more "static" balance between rider and bike.
You say you have difficulty adjusting spoke tension but you don't say what the problem is. Do you have a spoke tensiometer? I consider it manadatory (you don't have to have a fancy electronic one although they're a pleasure to use).
> But on a road bike, you maintain that alignment with your body and the frame
I used to do this until recently. It is now a bad habit of mine. On a mountain descent you'll want to steer that road bike how you would a mountain bike by leaning the bike and counter leaning your body. The more gradual the turn and lower thd speed, the less it will matter.
1. Go around the wheel and use a tension gauge to make all the spokes equivalent in tension. Then go around and fix the lateral and radial runout.
2. Has to do with geometry and thickness of the tires.
To generalize the article even more, the way a bike turns is like this: for a given speed and radius through a corner, there is a necessary lean angle. That lean angle determines the camber thrust of the tires, which is the centripetal force that makes the bike turn. However, you also have to make the bike yaw, which means the front has to generate a greater sideways force than the rear. This is accomplished through adding steering angle to the front tire. The longer the bike is, the greater the difference that is needed between front and rear sideways forces.
Furthermore, the steering angle of the front tire is affected by the head angle (90-rake angle), and geometric trail (caster effect). The greater the geometric trail is, the more the tire wants to resist turning. The greater the speed, the higher this effect. Conversely, the slacker the head angle is (lower in value, greater rake angle), the more the front tire wants to turn into the turn (because the wheel axle lower in height with increasing steering angle).
The reason why you generally lean the mountain bikes under you are 2 fold. First, the bikes are longer, so naturally you need the greater difference, which means you need more force from the front. You would exceed the max slip angle of the front tire if you stayed upright, especially on looser dirt. So instead, you lean the bike more to engage camber thrust. Secondly, the tires on mountainbikes are designed with side knobs specifically for cornering, so you want to engage those knobs.
The opposite problem exists on street motorcycles, where the bikes need to be low enough to the ground to not backflip on acceleration, which limits the available bike lean angle. So instead, riders learn to hang off the bike. This in turn requires the front end to be turned more. As a consequence of this, bikes understeer or oversteer behavior is greatly depends on the front end geometry (rake and trail). The trail forces are magnified at the higher speeds, so you need careful tuning of things like fork offsets (which control trail), and rake angle, both of which are affected by suspension moving up and down.
Yet, on supermoto bikes (i.e dirtbikes with street tires, popular in europe), you don't have the ground clearance problem, so you can actually corner them either like street bikes with knee down, or dirt bike style while leaning the bike under you.
> On their own, these dynamic forces exerted by the rider’s legs barely affect anything about the distribution of the ground reaction forces – one can’t make oneself heavier by just pressing harder on the ground.
I'm not sure about this. Yes, static weight _is_ fixed, but a rider can vary their dynamic downforce considerably. Skilled off-road riders (i.e. mountain bikers) vary their dynamic downforce for various reasons, including traction.
As always, I'm up for a discussion on this; it is possible the conventional mountain bike wisdom is a butchered version of the physics.
> It may seem obvious once pointed out, but the two elliptical regions under the two tires are the only places where the bicycle interacts with the road and almost all of the rider-controlled forces have to act through them.
In the book Snow Crash by Neal Stephenson, there is a quote that goes something like this:
"Most cars have tires that only contact the road in an area about the size of your tongue. Hiro's car had big radial tires where the contact area was the size of a fat person's thigh."
Bartosz is the quality bar I aspire to when I write my blog posts. I've always added interactivity in mine, but they in no way approach the detail and polish that he puts into them.
This guy's content is seriously top notch. His recent article on Sound from a few months ago was astounding and probably the best article I've seen posted here.
E=(mv^2)/2 - so we put more energy accelerating the bike from 10-20m/s than 0-10m/s, no?
Yet a=F/m - which suggests the acceleration is proportional to force, which would suggest that applying force F for time t should speed you up 0-10m/s the same way as 10-20m/s?
I suspect the force applied to the pedals is not the force which is acting on the bike (counter-force of the ground-bike system) and this second force is somehow relatable to the current speed of the bike, no?
Common mistake: you are confusing energy and momentum, or power (rate of energy/work) and force (rate of momentum change). In fact, power at constant force is F.v (force time velocity), which solves your question.
If you don’t shift gears, then your pedals increase in speed as your bike accelerates. So your power consumption goes up with speed even though force is constant.
Riding bicycle - as a skill is awkward and fascinating. It was established at very old times and so has remained. Imagine bicycles were invented today, its a product that nobody would buy. It takes lot of learning, falling, injuries, and for a lay person it looks awkward and risky.
If we generalize this, we are missing out on some skills, which are awkward but which our bodies and nervous system can learn? but perhaps we are not trying to learn thinking its risky?
A few observations: (1) Don't skip the textual explanations; (2) My favorite part is the wheel and spoke analysis; (3) Never stop improving your biking skills: it isn't just your legs; use your whole body!
P.S. For offroad riders (i.e. mountain biking): some things to look up if you don't know them: the "attack" position; the "cockpit"; pumping; row and anti-row motions.
Okay this is amazing. After checking the sources - I don't see any 3rd party libs.. This to my eyes looks like homegrown js (sources aren't transpiled).
As a fellow cyclist I've always thought about the physics on rides, it's why changing up the gear and getting the difference feels so good, but I don't think I could ever go into this kind of detail.
Nice demo of countersteering. When you jerk the slider quickly to the right, you can see that the right handlebar briefly lunges forward (left steer) before the steering recovers to the right. It's still noticeable with smaller/slower movements of the slider, but not as much.
I dream of building a bike with 1-2 dozen little wheels, and this frees up the design of the frame completely. Power would be given by little electric motors. The single point of failure represented by a single wheel would not be a problem anymore.
I’m not even done with reading, but i’ve been very interested in bikes and how they work for quite some time now and I can confidentially say that this is on of the best writeups there is.
Thanks to the author for making this
I don't understand the first three-arrowed diagram with the wall. Why two pushing arrows, at the front and the back of the crate but only one pushing from the wall to the crate, seemingly unbalanced?
All those mechanics are explained further down. There is a whole segment in the visualizations dedicated to steering and how you steer the othet way first.
The first animation is sort of wrong. To turn right on a bicycle, you actually steer slightly left (and vice versa). It's very jarring to see the wheel rotated in the same direction of the turn at extreme lean angles -- if you do that in the real world, you'll crash.
No, I don't think it does. Counter-steering is only a feature of a turn being initiated. Once the turn is in progress, the front wheel will very much be pointed in the direction of the turn.
Based on my experience, I believe that's not true. You counter-steer through the turn or your momentum would push the bicycle-rider system upright (centrifugal effect). Pointing the front wheel in the direction of the turn will initiate countersteer in the other direction (i.e., getting out of the turn). (I ride bikes most days of the year, if that helps.)
Unless we are talking something like speedway motorcycling[1] a constant-rate turn is accomplished by, after the initial counter-steering, pointing the wheel in the direction of the turn, such that the self-uprighting tendency of the bicycle matches the speed at which it falls to the ground due to gravity.
If you kept pointing the front wheel to the other side of the turn, the bike would fall over. (This property is what you use to initiate the turn, but not to maintain it.)
I believe you are mistaken. At steady state turning the steering is typically pretty subtle, and of course you can oversteer and have that mess with your balance in the opposite direction, but some steering has to be there to get the wheel to go in the right direction.
I went outside and did some empirical observation. I think the stable equilibrium depends on how fast you're going. At low speeds the equilibrium is in the direction of the turn. At higher speeds it isn't. Angle of the turn / lean and bike+rider system weight might play a role, too.
ciechanow.ski pages are usually super performant for me, but this one is super laggy, especially widgets with the bicycle man/mesh. Anyone else experiencing this?
Wow. Beautiful piece of art, but I am not going to read it. For someone who has, is the length of the article proportional to the gained knowledge, or could that be expressed much more succinct?
> is the length of the article proportional to the gained knowledge
It is. But I'm going to go against the grain here and say that timewise it's not worth it (I'm biased as I already knew most of the things I saw in the article while skimming it). I would just watch the Veritasium video and move on with my life. Or go down a wikipedia rabbit hole starting at https://en.wikipedia.org/wiki/Bicycle_and_motorcycle_geometr.... I appreciate the author's work, but this type of content is not for me. I suspect it's also not for the other self-proclaimed 'nerds' in the comment section, I think people just appreciate the work put into it and the fact that it's not following the style of shallow short SEO driven content you frequently find online. I'm skeptical that even 50% of the people in this comment section actually read all of it.
N=1, but I read the ones I'm interested in top to bottom. I didn't read this one specifically, but I finished the ones about lenses and mechanical watches in one sitting.
If it's about something that's really interesting to me, his work is absolutely fantastic. If it's not, I'll still take a peek because I like playing with the animations.
I've loved every article he's done so far. He only publishes about once a quarter and usually his articles are ~2 hours long. I've yet to be unimpressed.
>> Once mastered, the simple action of pedaling to move forward and turning the handlebars to steer makes bike riding an effortless activity.
Except you don't really turn the handlebars to steer, movement is far more than just pedaling and it's never an effortless activity if done right. Everything else in this sentence is correct though ;)
This is a great article. It showcases lots of the "simple, but surprisingly advanced" things surrounding bicycles. Which was what got me hooked in the first place. The visualization of how you have to turn right to go left is excellent. I've mentioned that fact multiple times here on HN, it's not commonly known, you just "do it" when you bike! And it explains why you sometimes can feel the curb "sucking" you towards it when you try to avoid it: you unconsciously avoid turning the wheel towards it, but that actually makes it so that you're unable to actually steer away from it!