I find it interesting. I have a passion for racing, the ability to program and find a lot of things wrong with "game" artificial intelligence being used in a racing simulation; see the very early posts of the thread.

That said it is a research project to see if it is possible to tackle the artificial intelligence from a standpoint of taking more realistic inputs/outputs, and trying to use reference points humans would use. I am making the video of progress for myself to look back upon, and for others to see, visually, how some of the computations are working. Reading about an algorithm is nothing compared to seeing a video of that algorithm in motion.

I decided I would make a video of my progress, and that meant programming the algorithm in a visual way. I think the results are spectacular, though not quite the final product.

This video is not a permanent video It will be deleted and replaced with another at a later date, when the actual racing line is computed. Currently this is showing the computation of the center line of the track, and at that you can see what I described above where it is not doing so perfectly.

Enjoy: Computing the Centerline on Youtube

Heh, that is because it was not suppose to be an ftp link, I have now switched it up! Good catch I will be sure to double check that in the future. Should be working now.

Yes, this is documented in the layout format and I actually had them using the z component too. 90% of the cones were great, but a handful were lifted much higher and it looked odd, so I decided to flatten my representation, at least for now.

EDIT: More Progress! I have the center-line of the track computing itself, just as I described a few posts back.

Screen shot here

However, as you see it has some issues if the person placing cones makes sharp turns. I think I need to do this a little better or more robustly, but that is going to require a bit more thought. I have a few ideas, such as blending the normals while going along the left edge, but even that might not work completely.

Last edited by blackbird04217, Tue, 24 Feb 2015 19:45.

Guess I will keep posting if only for my own amusement looking back on this project. I have made some progress and got my lfsScanner class to grab data from layout file that will resemble the reference points. Currently I have two types of reference points: LEFT_EDGE and RIGHT_EDGE. Left edge is resembled by place blue cones in LFS, and the right edge is the green cone. It is critical that when placing cones, they are placed in order going all the way around the track, otherwise the scanner will just get random points of data, which would be hard to infer where the track actually is. (In the case of a hair pin, bridge, etc).

In the AI project, I placed yellow cones where all these reference points are. (On a flat surface as the LFS layout file lifts some for physics dropping). The yellow cones are not visible in this picture but dots resembling their orientation lines are visible, and shows the front stretch, turn 1, chicane and hill of FE1.

http://imgur.com/8fq52OA

A long ways from where it was, but I think this will be much better than previously. Using the data from the track edges I will now try to compute the center line of the track. This is not the best/racing line, but it will be the first step in getting me there.

Okay, ignoring the fact that I think more people would be interested in this project than just programmers, I have picked FE1 as the track to start on.Not yet sure the car, but that is not a big deal.

My first step is to compute the theoretical best line, or the line the AI drive will try to drive around. Given that I am trying to resemble how a human would do this I have decided to call this portion of the AIRS project the "Track Walk".

During the Track Walk, the artificial driver will gather all the reference points around the track. Most importantly; Left Edge, and Right Edge. But any other reference points, like signs, cones, curbs, bumps, etc, would also be gathered at this time and stored in the drivers memory for later use. Though I am calling this the Track Walk, it is simply taking the reference point data and tossing it into the artificial driver, in no way is the artificial driver 'walking' the track.

Unfortunately, the Left/Right Edge reference points will need to be ordered as they go around the track, they can't just be random points, as that could cause misjudgment of a hairpin or chicane possibly. But this can be achieved, and is how one would walk around the track anyway.

Once that reference points have been gathered, the center line is computed from the Left Edge and Right Edge reference points. This will be achieved by taking the leftEdge[n] and leftEdge[n + 1], computing the perpendicular to this, ignoring height changes, and checking all rightEdge[m] and rightEdge[m + 1] until a collision occurs. Once this perpendicular 'leftToRightEdge' is found, placing the center point is simply a matter of scaling it back by half. Then continue with n = n + 1, until the track is completed.

This is obviously not the best racing line, yet. But it is the very first step needed to get there. The Track Walk will only be completed once the best line is found. I am starting this project from scratch, using very little to nothing of what I previously wrote. I plan to gather the Left Edge and Right Edge reference points from FE1 and I plan to make the AIRS project display what the AI driver is seeing, to later help with debugging and tracking. Previously I relied on print statements, which proved little help once the car got moving.

One problem I need to overcome to make this work with LFS is the PPJoy calibration. Last time I could not get it calibrated without a giant hack, it seemed holding the steering wheel at -15 degrees was 'straight'. I will have a copy of LFS meant only for the AIRS driver so that I don't need to fiddle with configurations like I did last time.

Lets see if I can do this project setup, and this portion of the Track Walk before June 1st 2013.

Good to know someone is interested. So, I have been doing a bit of research in what little time I do have for this project and I my plan is to plot out the points of one of the LFS tracks so that based on these points, I can then have the AI drive compute the best line.

My question to any of those who have some input, what is the easiest LFS club sized track configuration, that is not a rally track. I am thinking the size of AS1 or FE1. What do you guys think?

Is there any place I should revive a thread that might see more traffic than the programmer forum? I'm thinking this topic is interesting to others more than just programmers, even if it might be a touch technical.

Thanks for the input guys!

I've been back and forth about using LFS vs creating my own physical simulation for quite some time, I am currently leaning towards using LFS more than I have in the past. I read through some of my hesitations, where I can't get the information per tire, and I think a few members who were actively interested said it right; is that information really needed?

If anyone can get that replay working, it will show in 2010 I had an LFS car driving around from point to point. However it should be obvious to anyone who read this thread, that is not how I want the AI to work. It did prove that I could get the AI driver to aim the car where I wanted though.

I am taking a step back from LFS or building my own simulation. The very first part of this project should have been, "find the best racing line". Given all the reference points for the left and right edges of the track, I need to create a best line through this. I should be independent of the simulation as all it requires is the data.

Anyone here even/still interested in following this old project?

Does the replay in this post work for anybody?

I keep getting OOS errors, even when using 0.5Z 28, which is what it was recorded on. I was hoping to get a video of this, and have very much been considering jumping back on this project. A lot of good ideas started coming to my mind again and although it never got beyond 'theory' before, there is a lot to move forward with.

Thanks for trying.

They both have their pros and cons. iRacing has the best feeling tracks. Period. The new tire model is coming along, but I still enjoy the feel of the LFS tires. LFS is (or was, considering the last time I was very active) great for casual pick me up racing; especially when you get to know other racers. iRacing is much better with the competitive aspect, and you will find yourself battling for championship points whatever your interest.

Expect to spend $300 for a solid racing season in iRacing, but once you've got the tracks, the price drops quite a bit, to 'just' the subscription. Worth it? Well, that is arguable, but to me I haven't regretted my decision to do so. I didn't like it when I had some but not all tracks of a season, that was very annoying.

I don't like the idea of not being able to communicate with the iRacing community when my subscription ends, but for now, I don't see my subscription ending for a few years. They do have incentives that help a bit, honestly. Take $500 and tell me how far you get racing in real-life?

LFS on the other hand, suits the casual person/racer much better. If you're looking for a race here, or there. Then it is the right call. Setting up LFS is much easier, and you can easily turn it on/off without hesitation. I find in iRacing it has taken much longer to setup, and I can't always race on my own personal 'pick it up' schedule, I may have to wait 5 minutes, or run a time-trial while waiting for a qualifying/race session. But the racing is, in my experience, much cleaner; like the league racing in LFS.

So, they are each amazing in their own aspects. LFS in simplicity and casual pick-me-up racing. iRacing for real environment, competitive racing.

Since when does SLI work with 3 monitors? I do vaguely remember reading about this with the 200 series+ drivers, but I also remember it didn't work for my particular situation. Perhaps it was the 400 series+? But my gut still goes with that won't work? Anyways- good luck, hope it works for you.

Quote from CheerioDM :

More recent Nvidia cards will do three displays like ATI has Eyefinity.

I believe you did say that.

And you _still_ have ignored my question, and most of my what thoughts I've put into an answer for you. I can't help those who can't help themselves.

The windshield and mirrors don't give you that information.

+1 to removing the map feature altogether.

I didn't mean three outputs as in three outputs, I meant it as in three WORKING outputs. I do realize the difference, and was talking about the more recent nVidia cards that can handle three displays. The card I was talking about was the: GTX 560ti 2Win

Everything I said still stands. And I am still not sure what is the issue with SoftTH is for you?

Last edited by blackbird04217, Sat, 28 Jan 2012 17:22.

I am sorry to say without TH2G or SoftTH you will not be able to do this with two cards. SLI or not. The GTX 590 would allow this, but that card is outrageously expensive and out of stock for as long as I've noticed.

I have a GTX 280 and 520ti? Using SoftTH there is no frame drop in LFS with full three-screen support. Using iRacing however I needed to play with the settings forever, and the primary slowdown is the transfer of the buffer from the primary card (280) to the slave. I am not sure the power behind the 430, I know a 460 could be a primary and run fine.

It is _possible_ there are other software solutions like SoftTh, I've made something like it before with little success, but the fact remains it would still be software based and have inherent performance issues.

I can't speak about TH2G, though being a hardware solution it shouldn't have any issues assuming your card can render the full buffer fast enough, I assume it can. But it is expensive, and had other limits that turned me off from trying it.

May I ask why you are so against SoftTH? Because it is ultimately your only nVidia option with your current setup; that I am aware of. They do have a GTX 560ti 2Win with three outputs, maybe that is a viable option for you to buy?

Good luck.

Last edited by blackbird04217, Sat, 28 Jan 2012 17:21.

Quote from shiny_red_cobra :

Besides, the engine would stall anyway if you only feed it exhaust gases, there's not enough oxygen to maintain combustion.

I believe this is deemed common sense to anyone above the 6th grade- perhaps lower.

After a quick search I was surprised not to find this. But LMAO, what a great idea! Unlimited power;

http://www.eugeneleafty.com/DE ... stions%20%28pg%201%29.htm

I know, bumping an old thread. But some of you have been very interested so I decided I would post the point of interest writeups I did for my scrapbook project. 6 months to walk 2200 miles, over 2 years to finish the scrapbook...

This probably is not as nice as it would be with the pictures; and it is not ordered in anyway. It may not make much sense to people besides me. Perhaps the writeup in the first post was a better summary of the trip - but I post this on the chance that someone might enjoy it.

http://www.timbeaudet.com/goodies/at2009/at09_scraps.pdf

Given your being tethered, are you too laggy for the other players on the server? When I was using a satellite connection I had to stick racing with close friends, or those that knew of my crappy connection - because a jumping car is quite annoying to people with good connections [myself included]. Especially when drifting, the car is less predictable to others; even if it looks fine on your end. Just a consideration.

Perhaps this is a cause for people banning? My experience people ask you to leave before banning/kicking - not always, but generally. The servers that don't are servers I wouldn't be a part of anyways.

Quote from E.Reiljans :

Because it doesn't creates any entries in registry.

It does if you allow/want it to; for file associations.

This is on record, for watching later. Although my excuse for not watching it was to be sleeping... I see how well that plan worked out.

partan - you are correct with the adjustable bit, but for that exact reason it is also impossible to see the car in the mirrors, as the mirror 'cam' is in the center of the car facing backwards, so you would see a large chunk of the inside of your car on all mirrors.

That said, LFS could probably use an update on this system, and render each mirror at separately, at their own angles as an option, leaving the current route as a basic mirroring system.

[bump]

With the year being more than half way over, I figured it was time to check in on our goals.

Quote from blackbird04217 :

I plan on releasing my indie project, which I was hoping to release in 2010, but it continues, depending on available time.

I would like to build my next PC, but that depends on extra finances.
I would like to get my motorcycle fixed up and go riding more this year.
I would like to go on a few weekend long hiking trips, hopefully including my dad for some of that 'quality' time.
Perhaps I may continue the pay off the smaller student loan, I will have a better chance starting the new-year with a solid job.
Head-to-Head Racing Series will make a return, in some fashion or another.
I'd like to start my other planned league(s), with time permitting.
Maybe finish my scrapbook from my adventure almost 2 years ago!
Maybe go to the LFS Karting Event, cross the puddle for the first time and hangout.
Maybe I will create a more realistic reading/writing goals of like 12 books and 12 2-5 page stories.

Heh, I've been slacking, a lot.

- The indie project died off as soon as I got this new job - which is a pity because I believe you guys would love it.
- I have bought some PC upgrades; mostly an SSD, which is being used and will be in the next build.
- I did get my motorcycle on the road, and have been riding it, a lot more and will continue to do so until it is too cold.
- I have gone out hiking once, with my dad, for a weekend - though we are planning one more.
- I have only been making minimal payments on both my loans, while trying to build up a solid base in savings. I was hoping to have started really putting money towards the loan this month but other things are building up, which means it is likely I will have $1000 to pay January 2012 on my small loan.
- I have not touched my scrapbook, sim racing hasn't seen much time, lets face it I haven't seen much freetime at all this year. Work is far too time consuming; I've worked too many late nights and weekends that even had I tried organizing an event, I'd likely have had to cancel it.
- I have not wrote any short stories although I have ready a handful of things, probably not as many cover to cover though.

So, with that I am financially aiming to knock off the little loan as much as possible, but will not be able to pay it off without dipping into savings - which I've been considering. I need to get my mind set for writing/reading, but lately I've been trying to practice my artistic skills, something that would greatly help me when I do try working on indie-game projects.

How about you guys?

That brings back memories. Glad some people are still reading this, I had thought it was long dead and only living on in my memories.

Quote from fnixws :

So much for people saying its not possible and the posted SS was "normal".

Not saying this is directed at me, but I didn't say it wasn't possible - I didn't know how to do it though.

I did mention the first posted screen shot was normal - but that's based on personal opinions, and is how I feel more natural with the view. To each their own, glad you were able to get what you wanted.