In recent years, improvement of in-use fuel economy is required with tightening of exhaust emission regulation. We assume that one of the most effective solutions is ACC (Adaptive Cruise Control), which can control a powertrain in detail more than a driver. We have been developing a fuel saving ADAS application named “Sailing-ACC”. Sailing ACC system uses sailing stop technology which stops the engine fuel injection and disengage clutch when the car do not need acceleration torque. This system has a potential to greatly improve fuel efficiency. In this paper, we present a predictive powertrain state switching algorithm using external information (route information, preceding vehicle information). This algorithm calculates appropriate switching timing to sailing stop mode and acceleration mode to avoid braking loss. To design switching algorithm, we clarify the characteristics of driving technique called “pulse and glide”. This is a traveling method to repeat acceleration and sailing stop alternately to improve fuel efficiency. Our result shows that driving with “pulse and glide” is effective if the most efficient point is selected during pulse phase under constraints of vehicle and powertrain system. Our predictive switching algorithm calculates switching timing to sailing stop mode and acceleration mode to generate a “pulse and glide” pattern. The predictive algorithm decides the timing to maintain the vehicle speed under the speed limit to keep a safe distance from a preceding vehicle using prediction of route speed limit and preceding vehicle speed. As the result of the evaluation experiment, it was confirmed that this algorithm improved fuel efficiency of Sailing-ACC in practical driving environment.