-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
HW2.5 capabilities
- Thread starter verygreen
- Start date
-
- Tags
- Autonomous Vehicles
I guess I'll post here too.
The latest snapshotting logic shows us that they actually have some quite advanced labels.
A snapshot trigger for my car requesting "label: construction" triggered for my car today and created this image:
There's a bunch of other labels requested like "Confusing lanes", "slope up/down", "barrier" and so on.
I guess I have an urgent need to drive around in strange places to see what else I can trigger
The latest snapshotting logic shows us that they actually have some quite advanced labels.
A snapshot trigger for my car requesting "label: construction" triggered for my car today and created this image:
There's a bunch of other labels requested like "Confusing lanes", "slope up/down", "barrier" and so on.
I guess I have an urgent need to drive around in strange places to see what else I can trigger
lunitiks
Cool James & Black Teacher
Mind blowing stuff!
So this must be training in action, right? Your car obviously ‘knows’ (or rather, suspects) when it sees a roadblock, and then uploads the img to mothership and they do the validation thing?
So this must be training in action, right? Your car obviously ‘knows’ (or rather, suspects) when it sees a roadblock, and then uploads the img to mothership and they do the validation thing?
I guess I'll post here too.
The latest snapshotting logic shows us that they actually have some quite advanced labels.
A snapshot trigger for my car requesting "label: construction" triggered for my car today and created this image:
There's a bunch of other labels requested like "Confusing lanes", "slope up/down", "barrier" and so on.
I guess I have an urgent need to drive around in strange places to see what else I can trigger
We've observed for some time now that the steering wheel prompt behavior on AP1 and AP2 changes when there are construction barrels in the camera's view (prompts much more often.) Interesting to see it's sending snapshots as well.
I guess it's more like a debugging/looking for corner cases stuff? They get a bunch of matches from people that they then validate by some other means?
The label btw is a 4096 binary bytes. Some output from NN, I wonder?
The snapshot thing is a very recent development, I literally got the trigger for this snapshot last night, so it's not something they request from all cars at all times.
NN obviously is trained to recognize certain things, so one of those things is "construction zone" I guess. So then they request snapshots of the matching labels.
The snapshot request here looks like this:
Code:
{"query":{"$and":[{"$eq":["@LegacyDebug.gear",4]},
{"$gt":["@TelemetryOutput.distance_travelled_m",2000]},
{"$gt":["@LegacyDebug.veh_speed_mps",5]},{"$lt":["@LegacyDebug.veh_speed_mps",80]},
{"$gt":[{"$sum":[{"$labelboost":"$BIG_4K_of_data","version":"0.1","camera":"main"},
-0.012629894464]},0.5]},{"$gt":["@VisionImageEmbeddings.main.timestamp_ns",0]}]}they only send the main one for the label requests.
The curve fitting now sends 4 cameras: main, fisheye and the B pillars (both)
The curve fitting now sends 4 cameras: main, fisheye and the B pillars (both)
We've had evidence that the NN was identifying construction barrels on AP1 and AP2 for several months now, based on changes to the hands on wheel prompts. It was not quite as cut and dried as the new snapshot code verygreen found, but it was completely predictable and discussed in a couple threads about AP.
Last edited:
strangecosmos
Non-Member
I guess I'll post here too.
The latest snapshotting logic shows us that they actually have some quite advanced labels.
A snapshot trigger for my car requesting "label: construction" triggered for my car today and created this image:
There's a bunch of other labels requested like "Confusing lanes", "slope up/down", "barrier" and so on.
I guess I have an urgent need to drive around in strange places to see what else I can trigger
TMC needs a "Wow" rating!!Probably a bit of both.... the problem is if their identify is off it doesn’t take a snapshot of an edge case right?
It would flag false positives (or rather whoever does later review), but not false negatives.
That's really fascinating. The B pillar cams sure seem to be the best ones for determining if your car is currently centered in your lane or not. The main camera looks pretty far ahead, so this could potentially be for validation that the new control algorithm is performing acceptably.
I didn't think they were wide enough angle to show you the lane lines right next to you. I would have thought the "repeater" cameras on the front fenders facing backwards are a better choice for seeing lane centering.
I decoded several of the curve snapshots. Some of them are comically bad (as in, I am in the middle of a parking lot, but given that it looks mostly at steering angle, I guess that's ok). HEre are two that are actually on the road:
Damn, looks like only on occasion did these cameras show lane lines. I’m inclined to agree with you, do not seem like they’re the best for validation. Not sure what they were hoping with regards to curves, compared to the fisheye.
Similar threads
- Article
