This paper deals with the problem of estimating the position of center of mass for a polyarticulated system (e.g. a humanoid robot or a human body), which makes contact with its environment. The only sensors providing measurements on this point are either interaction force sensors or kinematic reconstruction applied to a dynamic model of the system. We first study the observability of the center of mass position using these sensors and we show that the accuracy domain of each measurement can be easily described through a spectral analysis. We finally introduce an original approach based on the theory of complementary filtering to efficiently merge these input measurements and obtain an estimation of the center of mass position. This approach is extensively validated in simulation using a model of humanoid robot where (i) we confirm the spectral analysis of the signal errors and (ii) we show that the complementary filter offers a lower average reconstruction error than the classical Kalman filter. Some experimental applications of this filter on real signals are also presented.
IEEE Transactions on Robotics