Physics-Informed Deep Transfer Learning for sEMG-Based Multiple Joint Angle and Torque Estimation

Accurately estimating joint angles and torques is essential for human-machine interfaces, such as exoskeleton control and human-robot collaboration. Musculoskeletal models driven by surface electromyographic (sEMG) signals incorporate human physiological knowledge but are computationally complex, whereas data-driven methods offer faster inference but lack interpretability. To bridge this gap, a physics-informed deep transfer learning framework is proposed in this article, which integrates physical knowledge as a soft constraint into the data-driven method. Additionally, a novel neural network called convolutional neural network (CNN)–Mamba is proposed to implement the framework. It combines the local feature extraction capability of the CNN with the global modeling ability of the state-space model (SSM) known as Mamba. To demonstrate its capability to simultaneously estimate the angles and torques for multiple joints, the method was validated on two datasets: wrist-hand coupled motion (ten subjects, a total of 30 trials) and walking motion (eight subjects, a total of 32 trials). The average Pearson correlation coefficient between estimated values and ground truth for all joints exceeded 0.96, reaching a maximum of 0.99. Ablation and comparative experiments further confirmed the advantages of the proposed method. Moreover, our approach demonstrates comparable performance to model-based methods while achieving at least $14\times $ faster inference speed. Specifically, estimating the joint angle and torque for a motion duration of 1 s takes only 161.8 ms. Overall, our innovative approach provides an effective solution for estimating multiphysiological parameters across multiple joints in human motion, with promising applications in human-machine interaction (HMI).