my friend bought a ride from a waymo for shits and giggles. i was actually intrigued about how the car made decisions on its own and sorta nerd sniped me to learn more about machine learning (not llms).
there’s probably some evil thing the self driving car companies are doing that im not aware of, but I was just interested in the ML aspect.
I though all Waymo driving decisions were performed using mechanical Turk?
Essentially what they do is have one human operator watching ~20 vehicles at the same time. When one of the vehicles gets into a situation that the automation can’t handle, it alerts the operator to take manual control. The cars aren’t being remotely operated 100% of the time.
it seems so possible and innevitable in the late aughts. 20 years later and it seems to just be advanced cruise control.
I hate driving and like the idea of driverless cars, but I’d far more like to have better mass transit and more areas that are enjoyable to walk around in. More space for humans and nature, less for roads and parking.
I think Uber under pays me and other drivers to this extent:
But has $10 billion to invest in driverless vehicles to replace us rather than paying decently.
So…meh. Not a huge fan.
damn, that’s probably the evil part i was yet to learn about
Did you know that the less picky you are on choosing your routes (or in other words, you are desperate for money) the less they pay you? Great business
Waymo uses predefined driving maps so it’s a lot more reliable, or supposed to be… this is how it probably should be done.
Upper echelon on YouTube has a really great video on accident and reliability numbers from both waymo and Tesla. Tesla is shockingly bad in safety. I highly recommend the watch, it shows a serious level of fraud.
Self driving is great and all, but it’s kind of fixing a problem that should be fixed by better city planning and public transport
Ooh, I get to geek out for a bit!
I helped a friend get into waymo as an employee when it was still staff-only/non-public, and later got to attend a private event where I could explore the regional hq building freely, view the cars, the hardware that makes them go, the nav system of all the cars in the region in real-time, see video feeds and diagnostics in real-time, ride in a ‘beta’ style vehicle with wires and sensors very much visible, ask questions directly to technicians regarding details about the software, cameras, lidar, emergency situations… The whole nine yards. I have also been in a public vehicle that was able to override the geofencing and ‘guardrails’ for a couple trips as well, and see how that works, how the car communicates with hq when that happens (‘why are you doing this, is everything okay, etc’). Except for someone currently or formerly employed by waymo, I am possibly one of the most informed people about how it all works. Especially the Lexus and Chrysler vehicles, since I got special access to those.
That out of the way, you are correct. They run the cars with a safety driver while training/feeding data back to the regional hq while in a new area, so you might see cars with a person at the wheel (and possibly a passenger, sometimes with a laptop) while the car drives around, not stopping for passengers. They note issues and areas for potential problems, log many miles along the same roads at different times of day for an entire area, and will do this with multiple vehicles for 6-12 months, before having enough data, runs, low incident occurance, and high confidence before allowing testers to ride; my last information was that they still retain the safety drivers for several additional months, before letting the cars go ‘solo’ and open the area to the public.
The friend has moved to greener pastures but this data is between '15 and '23, I believe. I am signed up for the tester program but the service is not yet in my home area; I’m a few miles outside their current zone for my region. I’ll be in the service area this winter though, and am planning on taking a couple rides and refreshing myself on the current situation for the general public.
-
In order for these vehicles to operate, they must all be surveillance platforms. They are covered in cameras, microphones, radar, sonar, lidar, and other types of sensors. The more of these vehicles are on the roads around you, the more real-time surveillance data is being collected. And you better believe those cameras are doing license plate recognition of every other vehicle they pass, in case there’s any incident that would involve an insurance claim. Basically they are mobile Flock on steroids.
-
Training machine learning models requires data. The edge cases have the least data for training, because they involve unusual weather or road conditions, specific lighting situations, weird/poorly designed intersections, or other uncommon circumstances. Edge cases will never be trained out because there will never be enough data for each specific case to have a meaningful effect on the self-driving model. Edge cases present the highest likelihood of injury to humans, whether as passengers, other drivers, or bystanders. People will continue to die, and somewhere in a meeting room someone will be presenting calculations to a board about whether it’s worth investing in better safety controls for their vehicles, or just bribing politicians to shield them from regulations and lawsuits.
People will continue to die
People also die in droves daily with human drivers. The important point is whether self driving cars are safer than the average human, not whether they eliminate all accidents entirely.
-
I’d rather have trains and walkable cities
Unless and until we as a society address the trolley problems raised by self-driving cars—who and what determines who lives in a situation where a choice must be made—I can only look on with dismay.
This is a real issue, and we’ve not yet addressed it. If your car has a choice between saving you or saving a child, or another person, or any number of unusual circumstances made inevitable by the sheer number er of miles collectively driven, what does it do? What do we want it to do? How do we balance the scale between saving your life or sacrificing it to save others?
Outlandish situations may be rare but they will happen, and we need to decide how our machines will weight the lives they are asked to save or sacrifice.
It takes time to accurately analyze the situation, make a decision, and then also direct the car to where it decided to go. Current tech isn’t capable of doing this and even if future tech can, that’s not what it should be doing.
In that time the car could automatically apply intense braking, even if it destroys the car in the process, like those saw blades that detect being touched and near instantly stop. That would probably launch the driver forward, but keep in mind they also have seatbelts and airbags. The pedestrians have nothing to protect them, and as a driver it’s your responsibility to look out for them, so if anyone is to get hurt at all, it should be whoever’s in the driver’s seat.
It being referred to as the trolley problem of self driving is not great because it implies that the only option is to choose who dies when in reality there are other choices that can be made instead where potentially no one even gets hurt.
.I think they are wasted time, money and energy. They are a solution to problems that have been solved long ago in much better ways: better urban planning and public transportation.
A lot of people don’t understand how technology works and they just always have like some form of amnesia after we hear horrific reports from real journalists about horrible things happening with this technology. So the last time I checked, we live in a fascist state, duhhhh USA, and they are going after Palestinian protesters and people that don’t like ice. So if you don’t have the option to have a non-self-driving car, then you just got a cell phone connected trojan horse to drive you around wherever you go and so if the state wants to kill you, they can. Plausible deniability and a fine of the cost of doing business. Does anybody remember Ford’s technology where they can shut your car off? And have it drive back to the dealership? It’s a patent! So instead of, you know, getting all hot and horny about the features and benefits because you’re too lazy to pay attention and drive and operate, maybe you should think about the implications and connect the dots because we live in a fascist state. I want my autonomy and I want my freedom of speech and I don’t want the government to have that reach. Fuck gipity and the dum dum self driving car. I want the raw dog baby… or like walkable cities and fucking trains. These companies are scamming the public. Fiddling with the numbers and milking the suckers. I got trains on the brainz
I wouldn’t want one myself as I like driving but it seems inevitable that they’ll more or less replace human drivers at some point as they’re probably already more competent at driving than even a good human driver is.
A waymo pulled out in front of me when i had no stop and was going 40 mph. Next time I’m gonna smash and sue instead pf hitting the breaks
Can we have more trains, trams, busses coverage instead? Why do we need selfdriving cars? If you are not in a condition to drive, than don’t drive.
I would love the technology to advance enough so I could retrieve that time for myself. I don’t particularly enjoy driving.
And personally think that once most cars are self driving accidents are likely to go down, making the roads safer.
