Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

New Study: Waymo is reducing serious crashes and making streets safer

waymo.com

Post reply on HN
Print view View original

31–40 of 413 posts

Re: New Study: Waymo is reducing serious crashes and making streets safer

#31

Post by wffurr »

kfarr wrote: post #19

This is great and there’s another area of influence that I’ve heard other traffic engineers discuss: platoon pacing. A platoon is the word that traffic engineers give to a group of cars traveling together. A platoon is most explicitly visible on a corridor with signals timed for a green wave, but occurs in many other contexts. Human drivers often race when in a platoon— not even on purpose it’s just an instinct to go…

This also came up recently in a thread about speed governors: https://news.ycombinator.com/item?id=43812856 Just a few governor-equipped vehicles (e.g. from public fleets or prior speeding offenders) can reduce speeding on the whole road.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#32

Post by wffurr »

IrishTechie wrote: post #17
AIPedant wrote: post #7

Earlier quoted context omitted.

The problem is that Waymos can't replace cars (or even Ubers!) since they depend on human oversight and problem-solving. Even at a 20:1 ratio it is not feasible for autonomous vehicles to employ 10m people to account for every American on the road.

Americans only spend 3% of their time driving, so it's maybe closer to 300k than 10m. Still not scalable at that though so the key will be driving that 20:1 up, which seems very possible given enough time.

If they keep pushing the hours between requests down like I saw on https://www.researchgate.net/figure/Estimated-number-of-full..., that might be feasible.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#33

Post by xnx »

AIPedant wrote: post #7
floxy wrote: post #2

That's great news. I wonder how much insurance rates will go down when autonomous vehicles get popular. Seems like the liability portion could go way down.

The problem is that Waymos can't replace cars (or even Ubers!) since they depend on human oversight and problem-solving. Even at a 20:1 ratio it is not feasible for autonomous vehicles to employ 10m people to account for every American on the road.

This is a very confusing position. Every Uber has full-time 1:1 "oversight". Waymo has a support team that only directs actions (not remote driving) when the vehicle requests. I would be very surprised if the number of Waymo rides that need any intervention at all is greater than 1 in 20.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#34

Post by indigodaddy »

How do AI cars fare with those instinctual "decide which way to swerve in a split-second" scenarios that come up maybe once every 10-20 years over the course of a driver's history?? It's happened to me about 2-3 times and I've always made the "(assumedly) correct" split second swerve decision. Wondering if that is a "human/instinctual" skill and if AI cars do just as well or better, or perhaps not as good? I don't have any evidence backing this but my gut tells me these scenarios are something that a human driver would handle better than AI.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#35

Post by standardUser »

wkat4242 wrote: post #30

In Holland we have this saying (based on an old commercial): "We from WC Duck recommend... WC Duck". (Which is a toilet cleaning product) It was a funny ad at the time. Unfortunately based in reality more and more these days.

I'm quick to discount reports that are "by the industry for the industry", but few industries are as transparent as self-driving taxis due to the strict operating laws in most jurisdictions.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#36

Post by rozap »

buckle8017 wrote: post #14
carlgreene wrote: post #10

This will surely get some skepticism as it's a Waymo study, but it's nice to see a real‐world dataset this large at 56M miles. An 85 % drop in serious‐injury crashes and 96 % fewer intersection collisions is a strong signal that Level 4 ADS can meaningfully improve safety in ride-hail settings. Still curious about how much of that comes from operational design versus the core autonomy, but it’s a big leap beyond “nov…

It's an incentive problem. Uber/Lyft drivers are strongly incentivized to drive as quickly and aggressively as possible. The individual drivers are trading risk for cash. A company like Google isn't going to make that trade because it's actually the wrong trade across millions of hours.

There was a study a few years back that showed male uber drivers earned more than female drivers. How could this be so, when the dispatch algorithm doesn't discriminate? Turns out men just drive a little faster in the aggregate so they made iirc around 3% more money.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#37

Post by johnfn »

As someone who is often on SF city streets without a car - I bike and run a lot - I absolutely love Waymo. I am continuously seeing human drivers cut me off, perform illegal maneuvers (i.e. run red lights when I'm going through a crosswalk), and break various other traffic laws. All these things genuinely put people in danger. Just the other day, a guy started running a "no right turn on red" lane in SF, and when I pointed it out to him he floored his car - through the red - right in front of me and laughed at me as he sped away. To say nothing of all the times when cars will honk or give me the finger for doing normal things on a street, like walking on a crosswalk.

Waymo is like the most courteous, respectful driver you can possibly imagine. They have infinite patience and will always take the option which is the safest for everyone. One thing which really impressed me is how patient they are at crosswalks. When I'm jogging, a Waymo will happily wait for me to cross - even when I'm 10 feet away from even entering the crosswalk! I don't know if I even have that much patience while driving! I've had a number of near misses with human drivers who don't bother checking or accelerate for no reason after I'm already in the crosswalk. Can you imagine a Waymo ever doing that?

If I see a Waymo on the street near me I immediately feel safer because I know it is not about to commit some unhinged behavior. I cannot say enough good things about them.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#38

Post by anigbrowl »

buckle8017 wrote: post #14
carlgreene wrote: post #10

This will surely get some skepticism as it's a Waymo study, but it's nice to see a real‐world dataset this large at 56M miles. An 85 % drop in serious‐injury crashes and 96 % fewer intersection collisions is a strong signal that Level 4 ADS can meaningfully improve safety in ride-hail settings. Still curious about how much of that comes from operational design versus the core autonomy, but it’s a big leap beyond “nov…

It's an incentive problem. Uber/Lyft drivers are strongly incentivized to drive as quickly and aggressively as possible. The individual drivers are trading risk for cash. A company like Google isn't going to make that trade because it's actually the wrong trade across millions of hours.

I think the problem is a general one about drivers, not just ride-sharers. I live in a fairly busy area and I am beset by aggressive drivers any time I need to cross a busy road. So many drivers simply ignore pedestrians by default. Not that many of them have Uber or Lyft signs in the window, if anything commercial drivers tend to be a bit more careful in my experience because the downside risk is being unable to work any driving job.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#39

Post by matttproud »

femiagbabiaka wrote: post #28

Anecdotally, as someone who bikes a lot in SF, Waymo's are a lot safer than human drivers simply because they follow the letter of traffic laws. Stopping at stop signs, waiting for pedestrians to clear the box, following the posted speed limits, etc.

I was just on a business trip to San Francisco for a few days, and I observed the near opposite of this from the Waymo fleet in SoMa:

* Waymo vehicle creeping into the pedestrian crosswalk (while the pedestrians had right of way to cross), which caused someone to have to walk around the car into the intersection ahead of the Waymo.

* Waymo vehicle entering a dedicated bike lane and practically tailgating the bicyclist that was ahead of it.

These might be safer than human drivers in aggregate and normalized by kilometer driven, but they drive like humans — greedily and non-defensively. I wouldn't want one these anywhere near a high-pedestrian traffic area ever, and I feel the same about human-driven cars, too.

Re: New Study: Waymo is reducing serious crashes and making streets safer

#40

Post by D-Coder »

timewizard wrote: post #11
returningfory2 wrote: post #6

Earlier quoted context omitted.

Tens of thousands of Americas are killed every year in car crashes. The existence of a case or some cases where a self-driving car caused injury has zero value. What matters is the rate of cases per mile driven.

The US drives about 3.2 trillion miles per year. Waymo has 56.7 million miles over several years. Their percentage data is essentially useless. 50% of fatalities involve alcohol or drugs and are often single vehicle accidents. 25% involve youth or inexperience. 15% involve motorcycles. 15% involve pedestrians. What I really need to see is a complete breakdown of every accident a Waymo has had. Then I can start to com…

> 50% of fatalities involve alcohol or drugs and are often single vehicle accidents.

This suggests that Waymo is cutting traffic fatalities by 50% (per million miles) right off the top.

Post reply on HN