I agree that LIDAR or radar are better solutions than image recognition. I mean, that’s literally what those technologies are for.

But even then, that’s not enough. LIDAR/radar can’t help it identify its lane in inclement weather, drive well on gravel, and so on. These are the kinds of problems where automakers severely downplay the difficulty of the problem and just how much a human driver does.

You are making it far simpler than it actually is. Recognizing what a thing is is the essential first problem. Is that a child, a ball, a goose, a pothole, or a shadow that the cameras see? It would be absurd and an absolute show stopper if the car stopped for dark shadows.

We take for granted the vast amount that the human brain does in this problem space. The system has to identify and categorize what it’s seeing, otherwise it’s useless.

That leads to my actual opinion on the technology, which is that it’s going to be nearly impossible to have fully autonomous cars on roads as we know them. It’s fine if everything is normal, which is most of the time. But software can’t recognize and correctly react to the thousands of novel situations that can happen.

They should be automating trains instead. (Oh wait, we pretty much did that already.)

Even talking about it this way is misleading. An LLM doesn’t “guess” or “catch” anything, because it is not capable of comprehending the meaning of words. It’s a statistical sentence generator; no more, no less.

The fundamental difference is that the AI doesn’t know anything. It isn’t capable of understanding, it doesn’t learn in the same sense that humans learn. A LLM is a (complex!) digital machine that guesses the next most likely word based on essentially statistics, nothing more, nothing less.

It doesn’t know what it’s saying, nor does it understand the subject matter, or what a human is, or what a hallucination is or why it has them. They are fundamentally incapable of even perceiving the problem, because they do not perceive anything aside from text in and text out.

I kind of disagree with you, in that when I think about the standalone meanings of the words in each phrase, I think they do say the same thing.

The meaning of the words “You are welcome [to the help I gave you]” implies, to me, that there wasn’t actually anything to offer thanks over. You’re acknowledging their thanks, but telling them that they are welcome to take/use whatever it is you’re talking about. [EDIT: normally when someone tells me I’m welcome to something, I feel less compelled to ask and thank in the future. “You’re welcome to anything in the fridge”, for example.]

It does not imply, to me, that I would appreciate them returning the favour. That might be implied meaning in the phrase, but it’s definitely not what those words mean by themselves.

In any case, “You’re welcome”, “no problem”, “no worries”, etc… are all idioms that mean something different than what their individual words mean. The phrases as a whole carry a different meaning than the words themselves suggest.

That sounds like a problem from using too small of a drive. Every torque curve I’ve seen for brushless DC or AC servos is constant torque from 0 to about 75% rated RPM, and then starts to drop off.

Well, that’s why you use a proper servo drive. Yes, technically they oscillate at standstill, but it’s so little it literally does not matter. Closed loop servo control is a solved problem unless you’re trying to implement it yourself.

I don’t know why you’re getting down voted. You’re correct, steppers are used due to cost.

I disagree with all your points. What kind of servos are you talking about?

BLDC and AC servos maintain full torque at stop too, and have about 2-3× the torque of a stepper of similar size.

The only way a stepper can rival a servo for precision is with a high degree of microstepping, which is far from guaranteed positioning with open loop control.

I haven’t directly compared response time between steppers and servos, but I would be extremely surprised if there’s a significant enough difference to worry about. Most servo-controlled machines are larger and so are designed to accelerate slower than a printer, if that’s what you mean. This is intentional because inertia is a thing you have to worry about, not because the servo reacts to command changes slowly.

There are valid reasons steppers are used on printers, but it’s not because they have superior performance.

Cost is the short version, yes.

I don’t know what kind of servos everyone here is talking about that are less precise than open loop steppers. Low quality hobbyist stuff, I guess? Proper servo motors & drives are the standard for good reason for robotics, industrial CNC machines, and pretty much everything else that needs powerful motors with high precision. Much higher power density, higher RPM (good for increasing torque with a gearbox), equivalent or better precision, plus closed loop control is a huge capability and safety gain.

That said, good, industrial quality servo motors are 1) expensive and 2) aren’t made in small enough sizes to be comparable to the steppers on most 3D printers. Even the smallest industrial servo + drive I’ve seen is about 5x as big as the steppers on a personal 3D printer and costs $800ish. Obviously, both are deal breakers for a personal 3D printer.

3D printers are a fairly ideal application for steppers. The moving parts are small and light, meaning you both don’t need a large motor and the danger of slippage is lower. Plus, steppers are cheap.