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

Traffic Simulator

traffic-simulation.de

Post reply on HN
Print view View original

31–40 of 143 posts

Re: Traffic Simulator

#32

Post by yabones »

searedsteak wrote: post #14

Looks like maxing out acceleration solves all other problems. I guess we should require a minimum power-to-weight ratio for cars from now on.

Maxing out 'politeness', 'acceleration', and 'inflow' I could achieve nearly 7000veh/hr.

Probably impossible, since it would cause heaps of rear ending accidents. Maybe if driver assist features both prevent lane changes and optimize avg. speed.

Re: Traffic Simulator

#33

Post by parhamn »

pc86 wrote: post #19
vbtemp wrote: post #16

Things like this are cool. What I would be curious to see though, rather than setting global parameters (i.e., politeness), would be to have each agent have its own politeness score (as well as other attributes). Models like the one linked to here work as if each agent is a particle, rather than autonomous decision-maker adapting to their circumstances locked in long-term, iterated games with other anonymous drivers.…

This would be a neat reinforcement learning project. > Some places the drivers are so polite to the point it really makes things dangerous I've known people like this, who will approach a 4-way intersection and stop even when they don't have a stop sign and the perpendicular street does.

> who will approach a 4-way intersection and stop even when they don't have a stop sign and the perpendicular street does

Not the main point but I never liked how traffic signs aren't affirmative sometimes. In the case of the 4-way usually the stopping direction have a stop sign with a missing "All Way" sign below it. But thats not required in all jurisdictions. Nor is the non-stopping direction 100% sure their stop sign is still visible (shrubs, weather, etc) and can proceed at regular speed.

I'm sure there are a ton of reasons for the way things are, I just think the outcome is you can't really ever be 100% sure what the correct thing to do is without slowing down and observing.

Re: Traffic Simulator

#34

Post by epanchin »

andrewstuart2 wrote: post #25
kharak wrote: post #22

Earlier quoted context omitted.

I've made the same observation. But I don't believe human drivers could reasonably take advantage of high acceleration, at least not as well as the simulated cars here. This is a great showcase of the usefulness of autonomous cars, though. Take humans out of the equation and traffic will flow.

The other thing that really seems to make the biggest difference (in combination with better acceleration) is following distance, which is another thing that presumably gets less important with autonomous cars because you don't really have to account for a relatively slow reaction time or poor braking. The observation on acceleration does make me wonder whether teaching proper merging etiquette better (reach freeway…

How do autonomous cars deal with cheap or worn tyres? Is there still a lot of allowance for braking distance?

Re: Traffic Simulator

#36

Post by bob1029 »

dogline wrote: post #35

I've always wanted to program something like this. What are good references to simulation programming to handle this kind of use case?

If you want to build a large scale, real-time simulation with many participants, you might want to check out some paradigms being used in the game development arena. Particularly concepts like Unity's DOTS/ECS approach.

Ultimately, the task is producing a good model of your domain and then organizing the data in such a way that you can quickly mutate a very large number of instances with each tick (if you are seeking real-time).

If you are not seeking real-time, you could probably do whatever the hell you want.

Re: Traffic Simulator

#37

Post by InitialLastName »

Cthulhu_ wrote: post #18
searedsteak wrote: post #14

Looks like maxing out acceleration solves all other problems. I guess we should require a minimum power-to-weight ratio for cars from now on.

In practice that would mean a lot more head/tail accidents, I've seen that happen plenty of times in traffic jams from over-eager drivers, sudden stops (either people trying to go too fast or not paying attention), etc.

Not to mention killing a lot more non-car road users who don't have access to the same acceleration.

Re: Traffic Simulator

#38

Post by bob1029 »

epanchin wrote: post #34
andrewstuart2 wrote: post #25

Earlier quoted context omitted.

The other thing that really seems to make the biggest difference (in combination with better acceleration) is following distance, which is another thing that presumably gets less important with autonomous cars because you don't really have to account for a relatively slow reaction time or poor braking. The observation on acceleration does make me wonder whether teaching proper merging etiquette better (reach freeway…

How do autonomous cars deal with cheap or worn tyres? Is there still a lot of allowance for braking distance?

Or weather/road conditions. Reaction time is irrelevant if you happen to be driving over an irregular/wet/oily/sandy/etc section of roadway at the moment maximum braking force is demanded.
Post reply on HN