Journal jtogel's Journal: Recent advances in car racing AI
With all the attention (rightly) given to the DARPA Grand challenge(s), it is a bit surprising that current car racing AI is so sloppy. Computer-controlled cars typically drive according to predefined racing lines and don't learn or adapt their driving styles to your driving. One notable exception is Microsoft's inventive AI in Forza Motorsport, where you can train "drivatars" to drive just like you.
At the University of Essex we are instead working on using evolutionary computation (such as genetic algorithms) and neural networks to control cars. The objective is to have the networks learning robust competitive driving behaviour without human input, and further to continue refining its behaviour when facing new tracks and opponents. So far we have come pretty far in the case of a single car on a track, and we are making progress on the two-car case. More details here, including videos and original papers.
At the University of Essex we are instead working on using evolutionary computation (such as genetic algorithms) and neural networks to control cars. The objective is to have the networks learning robust competitive driving behaviour without human input, and further to continue refining its behaviour when facing new tracks and opponents. So far we have come pretty far in the case of a single car on a track, and we are making progress on the two-car case. More details here, including videos and original papers.
Recent advances in car racing AI More Login
Recent advances in car racing AI
Slashdot Top Deals