Multi-Joint Physics-Informed Deep Learning Framework for Time-Efficient Inverse Dynamics
By: Shuhao Ma , Zeyi Huang , Yu Cao and more
Potential Business Impact:
Helps robots move more like humans.
Time-efficient estimation of muscle activations and forces across multi-joint systems is critical for clinical assessment and assistive device control. However, conventional approaches are computationally expensive and lack a high-quality labeled dataset for multi-joint applications. To address these challenges, we propose a physics-informed deep learning framework that estimates muscle activations and forces directly from kinematics. The framework employs a novel Multi-Joint Cross-Attention (MJCA) module with Bidirectional Gated Recurrent Unit (BiGRU) layers to capture inter-joint coordination, enabling each joint to adaptively integrate motion information from others. By embedding multi-joint dynamics, inter-joint coupling, and external force interactions into the loss function, our Physics-Informed MJCA-BiGRU (PI-MJCA-BiGRU) delivers physiologically consistent predictions without labeled data while enabling time-efficient inference. Experimental validation on two datasets demonstrates that PI-MJCA-BiGRU achieves performance comparable to conventional supervised methods without requiring ground-truth labels, while the MJCA module significantly enhances inter-joint coordination modeling compared to other baseline architectures.
Similar Papers
Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics
Machine Learning (CS)
Teaches robots to move like real animals.
Deep Muscle EMG construction using A Physics-Integrated Deep Learning approach
Machine Learning (CS)
Lets doctors measure hidden muscle signals.
Deep Inertial Pose: A deep learning approach for human pose estimation
CV and Pattern Recognition
Lets computers track body movements without expensive gear.