A comparison between the extended Kalman filter (EKF) and the nonlinear sigma point Kalman filter (SPKF) for a real time satellite orbit determination problem, using GPS measurements is presented. Such comparison is based on testing the filters robustness for degraded initial conditions. The main subjects for the comparison between the estimators are convergence speed and computational implementation complexity. Based on the analysis of such criteria, the advantages and drawbacks of each estimator are presented. In this work, the orbit of an artificial satellite is determined using real data from a space borne Global Positioning System (GPS) receiver. This is a fully nonlinear problem, with respect to both the dynamics and measurements equations, in which the disturbing forces are not easily modeled. The problem of orbit determination consists essentially of estimating values that completely specify the body trajectory in the space, processing a set of measurements related to this body. In this orbit determination problem the focus is to analyze each filter convergence behavior in situations where the initial conditions are inaccurate, introducing since small up to larger errors in the initial accurate position conditions. Concomitantly another aim is to know how such inaccuracies affect the estimators performance. In this work, the extended Kalman filter (EKF) is compared with the nonlinear sigma point Kalman filter (SPKF) for a real time satellite orbit determination problem, using GPS measurements. The comparison is based on the assessing the robustness of the filters for purposely degraded initial conditions. The main subjects for the comparison between the estimators are convergence speed, divergence occurrence, flaws and statistical shortcomings. Based on the analysis of such criteria, the advantages and drawbacks of each estimator are presented. Here, the orbit of an artificial satellite is determined using real data from the Global Positioning System (GPS) receivers. In orbit determination of artificial satellites, both the dynamic system and the measurements equations are of nonlinear nature. Therefore one deals here with a fully nonlinear problem in which the acting forces as well as measurements are not easily modeled. The orbit determination problem consists of estimating variables that completely specify the body trajectory in the space, processing a set of information (pseudo-range measurements) related to this body. As far as this work is concerned, the more accurate GPS phase measurements are not used here, because the aim is not the search for accuracy, but a comparison of performance under different error levels of initial conditions. Besides using carrier phase measurements, the ambiguity resolution algorithm or any other artifacts to overcome such hindrance could eventually mask the results, misleading the conclusions. A spaceborne GPS receiver is a powerful means to determine orbits of artificial Earth satellites by providing many redundant measurements which ultimately yields high degree of the observability to the problem. The Topex/Poseidon (T/P) satellite is a nice example of using GPS for space positioning. Through an onboard GPS receiver, the pseudo- ranges (error corrupted distance from satellite to each of the tracked GPS satellites) can be measured and can be used to estimate the full orbital state.