A Trajectory Tracking Control Scheme of a Human Arm in The Sagittal Plane

This paper presents a trajectory tracking control scheme for the human arm moving in sagittal plane. The arm is described by a musculoskeletal model with two degrees of freedom and six muscles, and the control signal is applied directly in muscle space. To design the intelligent controller, an evolutionary diagonal recurrent neural network (EDRNN) is integrated with proper performance indices, which a genetic algorithm (GA) and evolutionary program (EP) strategy are effectively combined with the diagonal neural network (DRNN). The hybrid GA with EP strategy is applied to optimize the DRNN structure and a dynamic back-propagation algorithm (DBP) is used for training the network weights. The effectiveness of the control scheme is demonstrated through a simulated case study.