arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.03441cs.CV
收藏

CLoSD: 面向多任务角色控制的仿真与扩散闭环方法

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Tel-Aviv University(特拉维夫大学);University of British Columbia(不列颠哥伦比亚大学);Carnegie Mellon University(卡内基梅隆大学);Simon Fraser University(西蒙菲莎大学);NVIDIA(英伟达)

Guy Tevet, Sigal Raab, Setareh Cohan, Daniele Reda, Zhengyi Luo, Xue Bin Peng, Amit H. Bermano, Michiel van de Panne

AI总结:

该研究提出CLoSD框架,通过构建扩散规划器与RL跟踪控制器的闭环交互,融合扩散模型的多样运动生成能力与RL的物理交互优势,实现文本驱动的多任务角色物理控制。

摘要:

运动扩散模型与基于强化学习(RL)的物理仿真控制在人体运动生成领域具备互补优势。前者能够生成丰富多样的运动,可响应文本等直观控制信号;后者则能产出符合物理规律的运动,且可与环境直接交互。本文提出一种融合二者优势的方法:CLoSD,这是一款文本驱动的基于RL的物理控制器,由扩散生成过程引导以完成各类任务。研究的核心思路是,运动扩散模型可作为实时通用规划器,为鲁棒的RL控制器提供支持。为此,CLoSD在扩散规划器(Diffusion Planner,简称DiP)和跟踪控制器两个模块间维持闭环交互。DiP是一款响应迅速的自回归扩散模型,由文本提示和目标位置控制;控制器则是简单鲁棒的运动模仿器,持续接收DiP输出的运动规划,并反馈环境信息。CLoSD可流畅执行一系列不同任务,包括导航至目标位置、按文本提示要求用手或脚击打物体、坐下以及起身。

英文摘要:

Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment. In this work, we present a method that combines their respective strengths. CLoSD is a text-driven RL physics-based controller, guided by diffusion generation for various tasks. Our key insight is that motion diffusion can serve as an on-the-fly universal planner for a robust RL controller. To this end, CLoSD maintains a closed-loop interaction between two modules -- a Diffusion Planner (DiP), and a tracking controller. DiP is a fast-responding autoregressive diffusion model, controlled by textual prompts and target locations, and the controller is a simple and robust motion imitator that continuously receives motion plans from DiP and provides feedback from the environment. CLoSD is capable of seamlessly performing a sequence of different tasks, including navigation to a goal location, striking an object with a hand or foot as specified in a text prompt, sitting down, and getting up. https://guytevet.github.io/CLoSD-page/

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑