On the Accuracy of Inertial Parameter Estimation of a Free-Flying Robot While Grasping an Object

Abstract

When model-based controllers are used for carrying out precise tasks, the estimation of model parameters is key for a better trajectory tracking performance. We consider the scenario of a free-flying space robot with limited actuation that has grasped an object of unknown properties. The inertial parameters - mass, centre of mass and the inertia tensor - of the robot-object system are to be determined. In our previous works, we used a parameter estimation algorithm where truncated Fourier series were used to represent both the reference excitation trajectory and the executed one. That algorithm is the focus of this paper, along with a study of the factors that could contribute to a loss of accuracy in the obtained estimates. Simulation results with the Space CoBot free-flyer robot are used to find the causes of the latter: first, a modified version of the minimum condition number criterion is used to generate feasible excitatory trajectories. The results are compared with those given by the maximum information criterion to check for better excitation. Next, an appropriate number of harmonics has to be found for the Fourier series, which will be used to fit the measured data. This is done autonomously, based on the least squares residual. Finally, the relation between input saturation while executing the excitation trajectory and the errors in the resulting parameter estimates is studied.