A new motion control method for omnidirectional intelligent wheelchair based on improved Fuzzy Support Vector Machine

This paper proposed the FSVM (Fuzzy Support Vector Machine) based on affinity to achieve the intelligent wheelchair motion control. The gravity center, which can be computed by calculating the weights of four force sensors under the wheelchair seat, is the key factor to determine the intention of movement of the user. The improved fuzzy membership function of FSVM can reduce the effect of clustering gravity center caused by abnormal clustering gravity center data generated from malfunction. Comparing with the traditional SVM (Support Vector Machine), the improved FSVM algorithm has lower error rate. This paper further validates the practical feasibility and validity of the proposed control algorithm. The experiment results show that the proposed algorithm can improve the precision of omnidirectional intelligent wheelchair motion control.