Driving assistant is very effective to reduce the traffic accident by warning driver and supporting his operation. In order to give accurate alarm and support, driver's status has to be measured correctly and speedily. In this research, we proposed a novel method to estimate the driving posture only from the pressure distribution between driver and car seat using a soft sensor sheet. Many pressure distributions for several driving postures were measured to create classifier using supervised machine learning method. The effectiveness of the generated classifier was verified using testing data and continued driving motion data.