Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors

2026-03-17

AI Summary

Reconstructing physically plausible and ground-interaction-consistent full-body human motion from sparse inertial measurement units (IMUs) alone remains challenging. To address this, this work proposes a novel approach that fuses sparse IMU data with insole pressure sensors, uniquely leveraging both foot pressure and IMU measurements to drive a physics-based, personalized digital twin for the first time. The method introduces a collaborative KinematicsNet–DynamicsNet architecture that enables high-fidelity, dynamics-consistent motion reconstruction within a physics simulation environment. Experiments demonstrate that the proposed method significantly outperforms existing IMU-only and IMU–pressure fusion approaches across multiple datasets, markedly improving global pose accuracy and physical plausibility. To support further research, the authors also release PRISM, a large-scale dataset combining synchronized IMU, pressure, and motion capture data.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

We propose Ground Reaction Inertial Poser (GRIP), a method that reconstructs physically plausible human motion using four wearable devices. Unlike conventional IMU-only approaches, GRIP combines IMU signals with foot pressure data to capture both body dynamics and ground interactions. Furthermore, rather than relying solely on kinematic estimation, GRIP uses a digital twin of a person, in the form of a synthetic humanoid in a physics simulator, to reconstruct realistic and physically plausible motion. At its core, GRIP consists of two modules: KinematicsNet, which estimates body poses and velocities from sensor data, and DynamicsNet, which controls the humanoid in the simulator using the residual between the KinematicsNet prediction and the simulated humanoid state. To enable robust training and fair evaluation, we introduce a large-scale dataset, Pressure and Inertial Sensing for Human Motion and Interaction (PRISM), that captures diverse human motions with synchronized IMUs and insole pressure sensors. Experimental results show that GRIP outperforms existing IMU-only and IMU-pressure fusion methods across all evaluated datasets, achieving higher global pose accuracy and improved physical consistency.

Problem

• human motion capture
• sparse IMUs
• insole pressure sensors
• physical plausibility
• ground reaction

Innovation

• physics-based motion capture
• IMU-pressure fusion
• digital twin
• humanoid simulation
• sparse wearable sensors