The success of model-based ECU-functions relies on precise and efficient modeling of the behavior of combustion engines. Due to the limited computing power, usually a combination of physical models and calibration parameters is preferred for engine modeling in ECU. The parameters can be scalars, 1 or 2-dimensional empirical models, such as look-up table for volumetric efficiency and effective area of the exhaust gas recirculation (EGR). A novel algorithm is proposed to automatically calibrate the look-up tables characterizing stationary functional relationships in ECU-function of the air system of a diesel engine with minimum calibration cost. The algorithm runs in the framework of online design of experiment (DoE), in which Gaussian process model (GPM) is adopted to approximate the relationships of interest. An active sampling strategy based on the concept of mutual information (MI) is implemented, which selects the optimal system inputs (engine speed, fuel quantity, air actuators, etc.) on the basis of input-space coverage, property of the relationship, uncertainty of the estimated calibration parameter and feasibility of the operation point. The main novelty is the prediction of the engine behavior invoked by the selected system inputs through exploiting the physical structure of the air system jointly with the data-based models (GPM) of the calibration parameters. Based on that, the uncertainty of calibration parameter is estimated using extended Kalman filter (EKF) and the feasibility of the working point is assessed by comparing the predicted system behavior with the engine limits. The algorithm was applied to calibrate the air system of a diesel engine equipped with high-and low pressure EGR, variable-geometry turbocharger (VGT) and variable valve timing (VVT) system. Utilizing the presented approach costing approx. 135 measurement points, a comparable calibration quality of the desired look-up tables was achieved, which was attained by conventional method consuming normally more than 800 measurement points.