FatigueFusion: Latent Space Fusion for Fatigue-Driven Motion Synthesis

TL;DR

FatigueFusion is a deep learning framework that synthesizes fatigued human motions by fusing fatigue features in a latent space, enabling realistic and subject-specific fatigue simulation in animation and biomechanics.

Contribution

It introduces a novel latent space fusion approach for fatigue-driven motion synthesis that operates without explicit fatigue input data, integrating algorithmic and data-driven modules.

Findings

Enables creation of fatigued motion variations and intermediate states.

Operates directly on joint angle sequences without needing fatigue data.

Supports seamless integration into existing motion synthesis pipelines.

Abstract

Investigating the impact of fatigue on human physiological function and motor behavior is crucial for developing biomechanics and medical applications aimed at mitigating fatigue, reducing injury risk, and creating sophisticated ergonomic designs, as well as for producing physically-plausible 3D animation sequences. While the former has a prominent position in state-of-the-art literature, fatigue-driven motion generation is still an underexplored area. In this study, we present FatigueFusion, a deep-learning architecture for the fusion of fatigue features within a latent representation space, enabling the creation of a variation of novel fatigued movements, intermediate fatigued states, and progressively fatigued motions. Unlike existing approaches that focus on imitating the effects of fatigue accumulation in motion patterns, our framework incorporates algorithmic and data-driven modules to impose subject-specific temporal and spatial fatigue features on nonfatigued motions, while leveraging PINN-based techniques to simulate fatigue intensity. Since all motion modulation tasks are taking place in latent space, FatigueFusion offers an end-to-end architecture that operates directly on non-fatigued joint angle sequences and control parameters, allowing seamless integration into any motion synthesis pipeline, without relying on fatigue input data. Overall, our framework can be employed for various fatigue-driven synthesis tasks, such as fatigue profile transfer and fusion, while it also provides a solution for accurate rendering of the human fatigue state in both animation and simulation pipelines.