Joint dynamics modeling and parameter identification for space robot applications

Long-term mission identification and model validation of in-flight dynamic behavior of manipulator systems in almost zero gravity and outer, i.e. hostile space environment is getting increasing value in technology demonstration missions based upon robotic applications, In micro-gravity environment the dynamic behavior of robotic manipulators is quite different from their on-g-round behavior, and on-ground simulated reduced gravity environment is, if at all, very cumbersome to realize. In-flight dynamic data, therefore, are most desirable to obtain with the main goal to update and validate mathematical models and hence to gain increased confidence in the modeling process also for more advanced robotized missions. To increase confidence in the dynamic modeling process based on multi-body systems and in ground-based simulations, the proper knowledge of system parameters, especially in the non-linear joints, is very important. In this paper, the aim is to represent the robot joint as close as possible to the reality. Therefore, a detailed mathematical modeling is performed where several non-linearities have been taken into account. In order to identify all the required parameters that accurately describe the robot dynamics, an integrated identification strategy is derived. This strategy makes use of a robust version of LS (Least Squares procedure) for getting the initial conditions and a general non-linear optimization method (MCS - Multilevel Coordinate Search - algorithm) to estimate the non-linear parameters. The proposed strategy has been divided into two parts: an initialization procedure and operational mode. in the normal operational mode, the linear parameters are identified by a RLS (Recursive LS) with a variable gain. Moreover, to detect unidentifiability, an initial test based on the singular value decomposition (SVD) of the measurements matrix is performed. The approach is applied to the Intelligent Robot Joint (IRJ) experiment that is being developed at DLR for early utilization opportunity on the International Space Station (ISS). The results using real and simulated measurements have shown that the developed algorithm and strategy have remarkable features in identifying all the parameters with good accuracy.