In this paper, the application of the learning automaton (LA) network with multi environments is proposed for the adaptive controller for ITS autonomous driving. The LA network, which we have introduced previously, has the ability of the learning which deals with both plural reinforcement signals and information of multiple environments at the same time. The feature is found to be useful for improving the response of the adaptation in the dynamic environment like the highway. In order to evaluate the practical advantage of using the network, we designed the simulational highway system, constructed the autonomous travel controller using the simple LA and the LA network, and executed comparative experiments which evaluate the performance of adaptation response and the collision avoidance. The results show that the performance of LA network with multi environments is superior to the one using simple LA application on its stability and safety.