GRACE：通过组合扩散-MPPI后验均值估计实现无梯度机器人动作生成
GRACE: Gradient-Free Robot Action Generation via Combined Diffusion-MPPI Posterior Mean Estimation
- School of Mechanical Engineering, Kyung Hee University（庆熙大学机械工程学院）
- Advanced Institute of Convergence Technology (AICT)（融合技术高级研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究提出GRACE方法，通过组合扩散-MPPI后验均值估计，仅用前向成本评估引导预训练扩散策略，构建成本条件引导后验并估计均值，在模拟和真实机器人上验证，比基线方法成功率高，能避免部署时障碍物。
AI中文摘要：
扩散策略可从演示中生成多模态机器人动作序列，但将其导向部署时的约束通常依赖于可微的引导成本。这排除了许多实际安全约束，如二元碰撞检查、关节限制和不可微的黑箱展开成本。我们提出了通过组合扩散-MPPI后验均值估计实现无梯度机器人动作生成（GRACE），它仅使用前向成本评估，通过模型预测路径积分（MPPI）控制来引导预训练的扩散策略。基于扩散和MPPI的常见得分上升结构，GRACE在每个反向步骤构建成本条件引导后验，并通过以扩散反向均值为中心的单个MPPI更新来估计其均值。对于可微成本，GRACE在一阶匹配协方差近似下恢复传统梯度引导。在模拟中，GRACE比基于扩散和采样的基线具有更高的成功率。在真实的7自由度操纵器上，GRACE避免了未引导的先验在每次试验中都会碰撞的部署时障碍物。代码和实验视频可在该https网址获取。
英文摘要：
Diffusion policies generate multimodal robot action sequences from demonstrations, but steering them toward deployment-time constraints typically relies on differentiable guidance costs. This excludes many practical safety constraints, such as binary collision checks, joint limits, and black-box rollout costs that are nondifferentiable. We propose Gradient-free Robot Action generation via Combined diffusion-MPPI posterior mean Estimation (GRACE), which guides a pretrained diffusion policy with Model Predictive Path Integral (MPPI) control using only forward cost evaluations. Building on the common score-ascent structure of diffusion and MPPI, GRACE constructs a cost-conditioned guidance posterior at each reverse step and estimates its mean with a single MPPI update centered at the diffusion reverse mean. For differentiable costs, GRACE recovers conventional gradient guidance under a first-order, matched-covariance approximation. GRACE attains higher success rates than diffusion-based and sampling-based baselines in simulation. On a real 7-DoF manipulator, GRACE avoids a deployment-time obstacle that the unguided prior collides with in every trial. Code and experiment videos are available at https://anonymous.4open.science/w/grace-70BB/.
