Upper limb musculoskeletal model as path generator for control a virtual orthosis: A dynamic neural network approach

This work presents the design and implementation of a reference path generator for a virtual version of a robotic orthosis based on a semi-parametric model of a neuromusculoskeletal system. The proposed generator is used to regulate the movements of the mentioned virtual orthosis (VO) as a preliminary stage in designing rehabilitation strategies. The generator considers a differential neural network (DNN) identifier, which predicts the angular positions and velocities of specific articulations in the upper limb using the raw electromyographic (EMG) signals as input. The DNN-based model is validated using experimental data from the elbow joint and the Biceps Brachii muscle collected from ten healthy participants. To regulate the movements of the VO, a controller based on the sliding mode considers the motion restrictions of the articulation of the extremity intervened by the orthosis. The proposed controller guarantees that the VO reaches a set point following a reference path related to the rEMG while the motion constraints are satisfied. The functionality of the proposed path generator was tested with a VO device. The results showed that the VO followed the angular movements of the elbow. All these results confirm the applicability of the proposed semi-parametric path generator based on a DNN.