Research on the Inverse Kinematics Prediction of a Soft Biomimetic Actuator via BP Neural Network

In this work, we address the inverse kinetics problem of motion planning soft biomimetic actuators driven by three chambers. Soft have been applied in many applications owing to their intrinsic softness. Although a mathematical model can be derived describe dynamics actuator, it is still not accurate capture nonlinearity and uncertainty material system. Besides, such complex time-consuming, so easy apply real-time control unit. Therefore, developing model-free approach area could new idea. To overcome these problems, propose back-propagation (BP) neural network learning actuator moving three-dimensional space. After training with sample data, BP represent relation between manipulator tip position pressure The proposed algorithm more precise than analytical model. results show that desired terminal achieved degree accuracy 2.46% relative average error respect total length.