ForceBody: Parametric Body Model with Ground Reaction Forces and Joint Torques

26.9 hours of motion data from 140 subjects across 10,386 trials. ForceBody pairs the SKEL parametric body model with measured ground reaction forces and inverse-dynamics joint torques. A subset of 8,652 trials includes per-frame, per-joint Monte Carlo uncertainty estimates for torque labels.

Use Cases

• Validate or calibrate biomechanical models based on measured ground reaction forces.
• Train machine learning models for motion prediction based on inverse-dynamics joint torques.
• Analyze uncertainty in biomechanical simulations based on Monte Carlo sigma_tau estimates.
• Develop control systems for humanoid robots based on real human motion and torque data.

Strengths

• Includes 10,386 motion trials from 140 subjects, providing a substantial sample size.
• 26.9 hours of motion data captured at 100 Hz offers high temporal resolution.
• 8,652 trials include per-frame, per-joint Monte Carlo uncertainty estimates (sigma_tau) for torque labels.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last updated 2026-05-07 10:15:43; freshness should be verified.

Provenance

Source

ForceBody

Collection Method

Pairs parametric modeling with measured forces and inverse-dynamics calculations.