Learning-based 3D human kinematics estimation using behavioral constraints from activity classification.

Journal: Nature communications
PMID:

Abstract

Inertial measurement units offer a cost-effective, portable alternative to lab-based motion capture systems. However, measuring joint angles and movement trajectories with inertial measurement units is challenging due to signal drift errors caused by biases and noise, which are amplified by numerical integration. Existing approaches use anatomical constraints to reduce drift but require body parameter measurements. Learning-based approaches show promise but often lack accuracy for broad applications (e.g., strength training). Here, we introduce the Activity-in-the-loop Kinematics Estimator, an end-to-end machine learning model incorporating human behavioral constraints for enhanced kinematics estimation using two inertial measurement units. It integrates activity classification with kinematics estimation, leveraging limited movement patterns during specific activities. In dynamic scenarios, our approach achieved trajectory and shoulder joint angle errors under 0.021 m and , respectively, 52% and 17% lower than errors without including activity classification. These results highlight accurate motion tracking with minimal inertial measurement units and domain-specific context.

Authors

  • Daekyum Kim
    Soft Robotics Research Center, Seoul National University, Seoul, Korea.
  • Yichu Jin
    John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Haedo Cho
    John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Truman Jones
    John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Yu Meng Zhou
  • Ameneh Fadaie
    John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Dmitry Popov
    Harvard University, Harvard John A. Paulson School of Engineering and Applied Sciences, Pierce Hall, 29 Oxford Street, Cambridge, MA, 02138, USA.
  • Krithika Swaminathan
  • Conor J Walsh
    John A. Paulson School of Engineering and Applied Sciences, Harvard University, 29 Oxford Street, Cambridge, MA, 02138, USA. walsh@seas.harvard.edu.