Tired Actor: Fatigue-Informed Character Control

2026-08-04

AI Summary

Existing physics-driven character animation methods lack physiological priors, making it difficult to simulate human motion under energy constraints and often resulting in unnatural behaviors. This work addresses this limitation by systematically integrating fatigue mechanisms from behavioral energetics into character control, treating fatigue as a proxy for limited energy availability. We propose a reinforcement learning framework based on the Three-Compartment Controller (3CC) model that enables motion imitation across diverse fatigue states within a unified architecture. Our approach significantly enhances the naturalness, physiological plausibility, robustness, and scalability of synthesized animations. The implementation is publicly released to facilitate further research in physiologically grounded character animation.

Abstract

Replicating human behavior with physics simulation has been a long-expected goal in character animation. Existing efforts have achieved impressive performance in imitating a wide span of general motions. However, most existing efforts could still suffer from unnatural movements due to the lack of biomechanical and physiological priors. Given this, we project our sights to advances in behavioral energetics, which demonstrate how energy use shapes human movements. In contrast, current character controllers typically assume the character is equipped with infinite energy over time. Inspired by these, we propose to adopt fatigue as a proxy of the finite energy limit, inject it into general character animation, and thoroughly investigate how fatigue introduces new characteristics to physics-based character control. Leveraging the Three-Compartment Controller (3CC) model, we managed to obtain a policy for general motion imitation under different fatigue statuses. Furthermore, extensive analyses are conducted to demonstrate how fatigue could influence the naturalness, scalability, and robustness of character animation. Our code will be made public.

Problem

• character animation
• fatigue
• physics-based control
• human motion
• energy limitation

Innovation

• fatigue-informed control
• physics-based character animation
• behavioral energetics
• Three-Compartment Controller
• motion imitation