Hacker News Reader

Comment by mabbo | Hacker News Reader

To the nay-sayers: yeah, this probably isn't the most accurate method, but you can use this in combination with other data to make better estimations.

For example, GPS has a common problem in areas with tall buildings where satellite signals bounce off a large flat sides of buildings, putting you a block away from where you actually are. Uber has done some fascinating work in this area by actually knowing the location and shape of all tall buildings in a bunch of cities- very clever.

But what if instead, the location estimator took in both the GPS signal and the inertial sensor. Sure, GPS says you just changed blocks, but the inertial sensor says you haven't accelerated from your previous location and heading.

Lots of noisy estimates, combined, can make for a pretty accurate estimate.

View on HN

Any location estimator worth its salt is already doing this through the use of a multi-rate EKF. On top of that, it takes into account the vehicle dynamics (i.e. cars can't move perfectly horizontally) to improve estimates.

The "novelty" here is the ML approach although I am not sure if that is particularly novel as well.

Exactly. I find it exceedingly odd that well-understood techniques like double integration and Kalman Filtering are being replaced by ML black boxes in the hope that ... what? They're going to rediscover what we already know? But in a format where we have no hope of figuring out what they discovered, so we can never bound their domains of acceptable performance?

Sometimes there are other regularities in the data that an ML algorithm can exploit; for example, if it can detect feet strike events in the IMU stream, it can compute an estimate of how fast someone is walking that is independent of integrating accelerations.

The benefit of ML over long-standing algos like kalman filtering for integrated navigation systems is they can can give you the occasional surprise when an unexplored edge case happens. People like surprises.

They can also give you the occasional surprise by diverging from the real trajectory, ex. trains doing barrel rolls

I've used ML to supplement straightforward heuristics before.

For instance, I built a fuzzy matcher for business addresses which was based on hand-rolled heuristics but used logistic regression to train a probability estimator that the match was correct and then hand-evaluated a few thousand matches so that the matcher knew the quality of results it was returning.

I am surprised that for dead-reckoning of an automobile position, one would not just use a something akin to a "mouse".

Why not compute optical flow from a camera on the underside of the car? Surely that would be more sensitive than an IMU?

For optic flow, you also would have to know the height above the road. That varies with vehicle load, tire pressure, speed bumps, etc.

It also would have to work on all kinds of road surfaces, day and night, in rain and snow, with different amount of sunlight, and with varying locations of the sun in the sky.

⇒ I don’t think this is as simple as you make it look.

Fuse it with inertial or depth data, and illuminate the surfacE

Factory systems almost always use the vehicle sensors in addition to GNSS, some early systems only had this ability since GPS wasn’t used.

Most cars have speed sensors, compass and steering angle sensors, but having that work with a smartphone is another problem.

Also there were these things: https://www.thedrive.com/news/34489/car-navigation-systems-b...

I think that's a cool idea. But I think the answer is as simple as it would require mounting a camera on the underside of the car. If you are going that route why not just point a camera at the speedometer right? Or integrate into the can-bus of the car and read it right from the onboard computer. I think the presented idea was probably something that was constrained by what you could do on a phone without interfacing externally.

Cameras get dirty and the underside of a car doesn't tend to stay pristine.

In any event, GPS + measuring how fast the axial spins would be able to get some pretty precises measurements. Two things most vehicles already have. The only issue is calibration at the start of movement.

Do you mean axle? I had the same thought, but I believe most every car has speed sensors on all 4 wheels for anti-lock breaks and I would imagine a way of telling the steering angle, so there are plenty of ways to get data; I'm sure more than I can think of since I'm just an occasional backyard mechanic, not an engineer.

Do you mean anti-lock brakes?

But yeah, most cars have sensors for all those things.

Yes, I mean brakes.

Dead reckoning [1] is not new, particularly also in car navigation. Particularly the inertial zeroing trick is common in pedastrian dead reckoning. Neural networks seem to be en vogue to improve this as well [2]

[1] https://en.m.wikipedia.org/wiki/Dead_reckoning [2] https://www.sbir.gov/node/1696357

>> Lots of noisy estimates, combined, can make for a pretty accurate estimate.

Or the people building the car could spring for the 100$ gyro rather than the 0.50$ phone-type gyro. With a reasonably-accurate gyroscope you can safely abandon most all the fuzzy data.

200x more expensive and a single point of failure? I can't see why they would pick that.

You'd need a better accelerometer too. For best results, you'd need three of each.

Reply on news.ycombinator.com