This is a submission from TSA member, JamboGT and is going to be used in his research for Uni.
Artificial intelligence is a topic that covers all types of game. However, unsurprisingly for those that know me, I want to talk about artificial intelligence in racing games. I study computer programming and game design and am currently working on my final year project, a form of adaptive AI in a racing game.
When making a racing game, I feel that one thing that is very tricky for developers is balancing the AI opposition so that players of all ability can not only defeat the opposition but be able to have a compelling and exciting race with them. Some players may be much faster than others so what do the developers aim for? The players running perfect laps or the players who make the odd mistake and go a lot slower? For many games the answer to this problem has been a technique known as rubber-banding.
For those of you that don’t know, rubber-banding is a method that artificially increases or decreases the performance of the AI opposition dynamically in order to match that of the player. This may be done by increasing the speed and acceleration of the AI, increasing the grip level of the AI or, in weapons-based games like Mario Kart, a better chance of picking up a good weapon.
Rubber-banding, for some games, is a great solution. It keeps the race close the whole way until the chequered flag. Would Mario Kart be Mario Kart without Luigi having a run at you on the final lap?! Burnout wouldn’t keep the same thrill until you crossed the line if the AI wasn’t using rubber-banding to catch up following a crash or a great burnout by the player. However, while this may keep the excitement levels up, there is always the feeling that the AI have been cheating, that the game is skewed unfairly against the player.
Sim games, such as Forza and Gran Turismo, tend not to use rubber-banding. GT has a difficulty that scales as the player levels up and Forza has a difficulty setting. There is no adapting of the AI as you race. This may lead to a “purer” race but also has its own problems. Namely, finding a skill level relative to that of the player. To put it simply: some people are good at racing games, some people aren’t, yet the AI has to race against a wide spectrum of abilities. This means that for some players they are far too fast and for some ridiculously slow.
For my final year project I decided to try to find a solution to this problem. To find a type of AI that can adapt to different players’ abilities dynamically yet not do it in a way that seems unfair to the player. A basic explanation is a system that tracks the players’ performance over a series of races and laps and then, over time, adjusts the AI to be able to provide a competitive opponent.
To do this, I need your help. Just down there is a link to a questionnaire (a very quick and painless questionnaire!) that I will be using to aid my research, the more data I have, the better my research so please take the time to fill it out.
Smartlover
I don’t remember which game it was, sorry, but I once played one where the ai adapted, but there was a “sweet spot”. A little slower, and you lost seconds, a little faster, and you had a hard race. Hit the “sweet spot”, and it was as if the game didn’t know what to do and you won easily. I actually could drive slower than my abilities and win easier than if I really went for it. It was a lousy game therefore. Real sorry I can’t remember the title though.
AshGraham99
Done, an interesting mix of games all with different ways of dealing with different driving abilities. One of the games where you could see where rubber banding was in place was NFS:Hot Pursuit. With the autolog times, you could have a better time than a friend who had the platinum for the game which required all golds, and still finish 4th. Sometimes could be slightly frustrating when you’d drove a full race and then pipped at the post. Wipeout worked well for me, where i’d be hopeless at elite level but the one down was really challenging. I’d say Race Driver:Grid had decent AI and always provided a challenge. I find racing games are best when you’re not under pressure to win every race, so as part of a championship which Grid did. Multiplayer is becoming more important and thats where the most exciting races happen, when you know you’ve not been slightly cheated by the AI or in some cases, cheated the AI by starting poorly and going on to win the race. I think thats an important point to mention, that sometimes rubberbanding helps the actual player aswell. Hope the rest of the project goes well!
blackredyellow
Done :) Hope it helps. Be interesting to see what you find and if your plan of an adapting AI can work/be put into practice. I expect your work to be published via TSA!
Jambo
I will be posting results and abstracts and all sorts of stuff!
priority 1 is the dissertation though! :P
Gadbury
Done. Some of the game series I have played but cannot remember how the AI behaved. So had to answer no. Anyway, I have completed the questionnaire. Good luck with the project – AI is very interesting but not so easy.
freezebug2
Survey done, good luck with the research and hopefully you’ll come up with some positive results. A subject close to my heart as you are likely aware Racing games are my favourite genre but I have known some games with dreadful Rubber Banding in my time ie. the AI don’t just catch you up from way back, they then go on to start racing faster or they catch you right up then go way back again, it’s a fine line and difficult to get right I guess, so this idea of yours of how to approach the way AI behave in racing games could be the answer to solving some of the problems.
shields_t
I wish I’d had a ready made focus group for my dissertation, might have ended up with a better degree. Filled in the questionnaire mate.
hazelam
the rubberbanding in racing games usually works to slow ai cars down when i play, to let me catch up. :)
and gran turismo had ai? i thought the cars were like scalextrix cars, well in previous generations anyway. ^_^
Crazy_Del
Survey done JamboGT and good luck with the research ;)
tonyyeb
Survey done. Anything to help a TSAer ;)
tom_lord
There you go Jambo, have fun, good luck, keep us up to date with the findings!