A Linear Approach to Optimize an EMG-Driven Neuromusculoskeletal Model for Movement Intention Detection in Myo-Control: A Case Study on Shoulder and Elbow Joints

Abstract

The growing interest of the industry production in wearable robots for assistance and rehabilitation purposes opens the challenge for developing intuitive and natural control strategies. Myoelectric control, or myo-control, which consists in decoding the human motor intent from muscular activity and its mapping into control outputs, represents a natural way to establish an intimate human-machine connection. In this field, model based myo-control schemes (e.g., EMG-driven neuromusculoskeletal models, NMS) represent a valid solution for estimating the moments of the human joints. However, a model optimization is needed to adjust the model's parameters to a specific subject and most of the optimization approaches presented in literature consider complex NMS models that are unsuitable for being used in a control paradigm since they suffer from long-lasting setup and optimization phases. In this work we present a minimal NMS model for predicting the elbow and shoulder torques and we compare two optimization approaches: a linear optimization method (LO) and a non-linear method based on a genetic algorithm (GA). The LO optimizes only one parameter per muscle, whereas the GA-based approach performs a deep customization of the muscle model, adjusting 12 parameters per muscle. EMG and force data have been collected from 7 healthy subjects performing a set of exercises with an arm exoskeleton. Although both optimization methods substantially improved the performance of the raw model, the findings of the study suggest that the LO might be beneficial with respect to GA as the latter is much more computationally heavy and leads to minimal improvements with respect to the former. From the comparison between the two considered joints, it emerged also that the more accurate the NMS model is, the more effective a complex optimization procedure could be. Overall, the two optimized NMS models were able to predict the shoulder and elbow moments with a low error, thus demonstrating the potentiality for being used in an admittance-based myo-control scheme. Thanks to the low computational cost and to the short setup phase required for wearing and calibrating the system, obtained results are promising for being introduced in industrial or rehabilitation real time scenarios.

Keywords: EMG; exoskeleton; genetic algorithm; myo-control; neuromusculoskeletal model; optimization; torque prediction; upper limb.

Figure 1

The experimental setup. (A) The subject wears the upper limb exoskeleton controlled in position and the HMD displaying the cursor and the target spheres in a 3D virtual environment. (B) The neuromusculoskeletal model adopted in the study and the electrodes placement. (C) The five end-effector positions lying on the sagittal plane explored in the experiment.

Figure 2

E_RMS and R² performance obtained in the experiment. Left and right columns relate to the elbow and shoulder joints, respectively. The first row reports the E_RMS performance, and the second row the R² performance. Each panel reports the performance for each subject and the averaged performance with the standard deviations. Asterisks mark the significance of the Bonferroni corrected post-hoc comparison tests (* < 0.05 and ** < 0.01).

Figure 3

The myoelectric Control Scheme. Raw surface EMG signals are pre-processed to compute the muscle excitation e(t). The neuromusculoskeletal model is used to predict the reference torques (Equations 2–6). Through the admittance control the predicted torques are used to generate the reference joint angles of the assistive device. The local controller is based on a position PD controller with gravity compensation. The measured joint positions are fed back to the PD controller and to the torque predictor.