We define micro hand gesture recognition system as which uses micro dynamic hand gestures within a time interval for classification and recognition to achieve human-machine interaction. Our Project Hug (Hand-Ultrasonic-Gesture), with ultrasonic active sensing, pulsed radar signal processing, and time-sequence pattern recognition is presented in this paper for micro hand gesture recognition. We leverage one single channel to detect both range and velocity precisely, reducing the hardware complexity. And to make use of sequencial range-Doppler information, high dimensional features are symbolized, which significantly reduceds the computation complexity and power consumption. A real-time prototype was released and an average recognition accuracy of 90.5% for seven gestures was achieved .