Force/position tracking control of fracture reduction robot based on nonlinear disturbance observer and neural network

Abstract

BACKGROUND: For the fracture reduction robot, the position tracking accuracy and compliance are affected by dynamic loads from muscle stretching, uncertainties in robot dynamics models, and various internal and external disturbances. METHODS: A control method that integrates a Radial Basis Function Neural Network (RBFNN) with Nonlinear Disturbance Observer is proposed to enhance position tracking accuracy. Additionally, an admittance control is employed for force tracking to enhance the robot's compliance, thereby improving the safety. RESULTS: Experiments are conducted on a long bone fracture model with simulated muscle forces and the results demonstrate that the position tracking error is less than ±0.2 mm, the angular displacement error is less than ±0.3°, and the maximum force tracking error is 26.28 N. This result can meet surgery requirements. CONCLUSIONS: The control method shows promising outcomes in enhancing the safety and accuracy of long bone fracture reduction with robotic assistance.