A self-supervised PINN estimates human joint kinematics and kinetics from sparse IMU data by enforcing physical plausibility via a body model, reporting RMSD of 8.7 deg and 4.9 BWBH% on walking and running.
The GRF is calculated as: Fy = −kζ(βpgc,y) (1 − b ˙pgc,y) /β with β = 300, stiffness k = 100 BW/m, damping b = 0.75 N s m−1, and Fx = µmax tanh(ˆµ)Fy, with µmax = 0.5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SSPINNpose: A Self-Supervised PINN for Inertial Pose and Dynamics Estimation
A self-supervised PINN estimates human joint kinematics and kinetics from sparse IMU data by enforcing physical plausibility via a body model, reporting RMSD of 8.7 deg and 4.9 BWBH% on walking and running.