Time-delay error compensation for POS based on PSO tuning SVM

Position and orientation system (POS) is widely applied in remote sensing applications, which provide high-accuracy position, velocity, and attitude information for remote sensing motion compensation. As a multisensory system, time-delay usually occurs during signal preprocessing, transmission, integration, filtering, etc., which decrease the measurement accuracy. As the POS motion parameter varies nonlinearly, the time-delay error can't be precisely compensated by the conventional linear method. To solve this problem, a novel time-delay error compensation method based on Support Vector Machine (SVM) is proposed, and Particle Swarm Optimization (PSO) is used to optimize the key parameters of SVM. In verifying the proposed method, a flight experiment was conducted. Experimental results show that the proposed method can effectively compensate the time-delay error of POS, and is more accurate than the conventional one.