Learning Realistic Athletic Sprinting Without Demonstrations

2026-09-10

AI Summary

该研究通过结合生物力学模型和GPU加速模拟，利用强化学习在无演示情况下生成逼真的高速运动控制策略。

Abstract

We present a muscle-driven simulation system for generating biomechanically accurate motion for high-speed athletic locomotion tasks that does not require motion demonstrations. Our approach integrates state-of-the-art biomechanical athlete models into a new, high-performance GPU simulator capable of running at 1000x real-time. High-throughput simulation enables large-batch reinforcement learning to train control policies that operate directly in the model's high-dimensional muscle excitation space, and are guided only by task-specific episode termination conditions and a reward that encourages maximizing speed while reducing forces needed to respect joint limits. These policies train within a few hours on a single GPU and generate "near visually realistic" motions for complete athletic activities such as a full 100-meter sprint or performing popular athletic locomotion drills like side-shuffling, backpedaling, and carioca. The generated sprinting motions also exhibit strong agreement with experimental data captured from sprinters.

Problem

• biomechanical
• high-speed locomotion
• motion simulation
• reinforcement learning

Innovation

• muscle-driven simulation
• high-speed locomotion
• reinforcement learning
• GPU acceleration
• biomechanical model