A heading angle control method is proposed for controlling underwater gliders to follow a straight line sampling path relative to the center of a dynamically moving mesoscale eddy. The constant velocity and constant acceleration kinematic models are employed as motion models of eddy center movements. The model parameters are identified from historical data of eddy tracks. A Kalman filter is developed based on the models and real-time satellite imaging data to estimate and predict the movement of eddy centers. Performance of the two modeling approaches are compared based on historical data, results show that the constant velocity model is preferred for eddy movement prediction when used for glider heading control. Both simulation and field experiments confirm that underwater gliders under the heading control, when used with the Kalman filter, are able to follow the sampling path autonomously with acceptable level of tracking error.