In a traffic system with HOV lanes, considering two modes of driving alone and carpooling, we proposed three kinds of travel cost functions for potential commuters such as carpoolers in HOV lanes, driving alone users and carpoolers in general purpose lanes. Assume that all commuters will experience a random travel time with discrete distribution during their trip, this paper compared the commuters' equilibrium choices of travel mode and travel route under the framework of cumulative prospect theory and expected utility theory. In addition, the sensitivity analysis on the proportion of driving alone users, the individual preference such as the reference point were conducted. The resultant observations show that the individuals' risk preference and reference dependence definitely affect the commuters' choices on the travel mode and travel route. When the proportion of driving alone users exceeds a critical value, the carpooling users will be better than driving alone users since they have higher cumulative prospect value. However, this critical value will be slightly overestimated under the framework of expected utility theory. [ABSTRACT FROM AUTHOR]