外观
论文arXiv 2610.1814715 天前
像这样行走：通过示例驱动扩散实现物理角色的风格化运动
原文链接：Walk Like This: Stylized Locomotion for Physics-Based Characters through Example-Driven Diffusion（arXiv 2610.18147 · 发布日期：2026-10-13）
Walk Like This: Stylized Locomotion for Physics-Based Characters through Example-Driven Diffusion
针对速度与风格独立可控的表现性腿式运动，提出示例驱动扩散框架，并在仿真人形角色和实体机器人上验证。
核心要点
- 现有数据驱动控制器通常需显式风格标签，难以利用大规模无结构运动数据并泛化到未见风格。
- 方法通过定制采样训练风格编码器，将其输出条件化自回归扩散模型以解耦风格与功能运动。
- 推理时输入风格参考片段和摇杆速度命令，生成由强化学习控制器跟踪的运动学参考。
- 注意力偏置与速度命令校正提升可控性和风格强度，展示稳健实时控制与连续风格调制。
验证范围与局限：验证范围为仿真中的物理人形角色和实体机器人上的实时风格化腿式运动控制。
英文摘要 (Abstract)
We present a real-time framework for expressive legged locomotion that enables independent control over velocity and style. Unlike existing data-driven controllers, which typically require explicit style labels for training, our method efficiently leverages large-scale unstructured motion data and generalizes to unseen styles. We disentangle style from functional locomotion through a tailored sampling strategy used to train a style encoder whose output conditions an autoregressive diffusion model. During inference, the user provides a style reference clip and a joystick velocity command. The diffusion model then generates a kinematic reference tracked by a reinforcement learning controller. To improve user controllability and stylization strength, we propose an attention biasing mechanism and a velocity command correction strategy. We demonstrate our method on a physics-based humanoid character in simulation and on a physical robot, showcasing robust real-time control and continuous style modulation. The results can be best seen in our supplemental video (https://www.youtube.com/watch?v=roFnS6N7nJ4).
作者：Joshua Aurand, Agon Serifi, Sammy Christen, Ruben Grandia, Espen Knoop, Marco Hutter, Moritz Bächer
来源
本页事实对应的公开页面，以原文为准。