Abstract: At present, the track type robot is widely used in the inspection robot of the fully mechanized working face. When the robot passes through the track connection, it will produce jitter. It causes an increase in the positioning error of the inertial navigation/odometer combination. In order to solve this problem, based on the integrated navigation algorithm of inertial navigation/odometer, a piecewise filtering method based on jitter detection is adopted to achieve autonomous positioning of the inspection robot. Based on the gyroscope data of the inspection robot passing through the track connector, a sliding window method is used to dynamically analyze the pitch angular velocity of the robot. The local maximum rising edge and local maximum falling edge are determined by calculating the derivative sum. When the maximum rising edge and maximum falling edge alternately appear, it is considered that the track connector has been recognized. The jitter detection is achieved, thus dividing the robot's motion state into stable operation state and jitter state. When the robot is in a stable operation state, both the gyroscope and odometer data are relatively stable. At this time, the inertial navigation/odometer combination navigation method is used for filtering and solving. The gyroscope error is corrected based on the characteristic that the gyroscope data should be stable near zero. When the robot is in a jitter state, the odometer may generate errors due to wheel slip and bouncing in the air. At this time, a pure inertial navigation algorithm is used to eliminate the impact of odometer errors on the integrated navigation positioning. The experimental results show that the jitter detection algorithm can accurately determine the track connections. The segmented filtering method based on jitter detection can effectively improve the positioning precision of the inspection robot. The average positioning error is less than 5 mm, meeting the precise positioning requirements of the fully mechanized working face.