Lane-change is one of the most difficult tasks of driving. A notable number of situations have to be considered simultaneously. A lane-change decision support model is developed in this study using the artificial neural networks (ANN). The advantages of the ANN approach lie in the learning capability. Due to its nature, the ANN model can consolidate various information surrounding the drivers and generate reliable results to help control the vehicles. Several preliminary validations and comparisons are conducted with the field survey data. It is confirmed that the ANN model mimics traffic characteristics more accurately. In particular, the ANN model can be adopted to individual driver characteristics. This reveals practical feasibility and significant market potential for customized in-vehicle equipment. (A*)
Samenvatting