SCRIPT: 面向语言驱动的物理仿真人体控制的可扩展扩散策略与多阶段训练
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
AI总结:
提出SCRIPT框架,通过联合动作-状态-文本扩散Transformer和多阶段训练(监督模仿预训练+混合奖励强化学习后训练),实现语言指令驱动的物理仿真人体控制,在文本对齐、运动质量和物理真实性上超越现有方法。
摘要:
从自然语言指令控制物理仿真人体是迈向通用具身智能体的关键一步。然而,现有方法仍受限于语义表达能力和物理可行性之间的张力,往往难以同时实现忠实的指令跟随、高质量的运动和稳定的长时程控制。我们提出SCRIPT,一种具有多阶段训练框架的可扩展扩散策略,用于语言驱动的物理仿真人体控制。SCRIPT的核心是联合动作-状态-文本扩散Transformer(JAST-DiT),它将动作、物理状态和文本表示为专门的令牌流,并通过联合注意力将它们耦合,使语言语义和控制动态之间能够直接交互。为了稳定自回归控制,我们引入了一种非线性历史条件机制,该机制保留密集的近期上下文,并从长期历史中采样越来越稀疏的线索。除了监督模仿预训练外,我们提出了一个后训练阶段,使用混合奖励强化学习(RLHR)进一步提高性能。通过将可学习噪声注入流采样过程,RLHR利用混合物理反馈和文本奖励在闭环模拟中有效改善运动质量和指令跟随。定量评估表明,SCRIPT在文本对齐、运动质量和物理真实性指标上均优于先前的最先进方法。此外,在1200小时的MotionMillion数据集上的扩展研究显示,随着模型规模的扩大,性能持续提升,突显了SCRIPT在大规模预训练中的稳健可扩展性。我们的代码将公开供未来研究使用。
英文摘要:
Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history. Beyond supervised imitation pre-training, we propose a post-training stage, further improving the performance using Reinforcement Learning with Hybrid Rewards (RLHR). By injecting learnable noise into the flow-sampling process, RLHR effectively improves motion quality and instruction following within closed-loop simulations using hybrid physical feedback and text rewards. Quantitative evaluations demonstrate that SCRIPT outperforms prior state-of-the-art methods, with gains across text alignment, motion quality, and physical realism metrics. Furthermore, scaling studies on the 1200-hour MotionMillion dataset demonstrate consistent performance gains with model scaling, highlighting SCRIPT's robust scalability for large-scale pre-training. Our code will be publicly available for future research.
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。