Being one of the most simple and basic driving scenarios, highway scenario can be one of the first scenarios to achieve autonomous driving. Both car following (CA) and lane changing (LC) are the most basic and frequent manoeuvre during highway driving task, and therefore become two key issues to focus on in recent researches about autonomous vehicle (AV). Different from conventional CA and LC researches that attach much importance to the character, psychology, perception ability, and driving experience of human drivers, more timely and accurate reactions based on fast perception and communication technology as well as the automatic actuator are hypotheses for this research. And based on these hypotheses, a modified intelligent driver model (MIDM) is proposed for AVs’ following behavior to alleviate the fluctuations caused by lane changing behaviors. As for lane change, decision rules based on signals from environment perception system instrumented in the subject vehicle are designed for the purpose of improving the traffic efficiency. Then, for validation, simulation environment of autonomous driving on highway is established in MATLAB. And simulations of the proposed models are finally carried out for comparisons with the conventional CA and LC models in terms of flowrate, time-space distribution, velocity, and acceleration of vehicles. The comparison results show that the models proposed in this article are more capable of achieving homogeneity of vehicle flow as well as reducing the fluctuations of transportation system, and the most important, improving the traffic efficiency. It is obvious that all these advantages are good for both single AV driving and the whole traffic system. This research can serve as a reference for both fully autonomous vehicle and intelligent transportation system (ITS) researches.