无需梯度的机器人动作生成，让机械臂避开障碍物。
GRACE: Gradient-Free Robot Action Generation via Combined Diffusion-MPPI Posterior Mean Estimation
- 用MPPI控制在每步反推时构建带约束的指导后验分布
- 真实机械臂实验中100%避障，未引导时全失败
- 适合有不可微约束的机器人部署场景
扩散策略可从示范中生成多模态机器人动作序列，但通常依赖可微分的引导代价来满足部署时约束，这排除了如碰撞检测、关节限位等不可微的实际安全约束。本文提出无需梯度的机器人动作生成方法GRACE，通过仅需前向代价评估的模型预测路径积分（MPPI）控制，引导预训练扩散策略。基于扩散与MPPI共有的梯度上升结构，GRACE在每一步反向过程中构建代价条件后验分布，并以一次中心于扩散反向均值的MPPI更新估计其均值。对于可微代价，GRACE在一阶匹配协方差近似下恢复传统梯度引导。仿真中，GRACE成功率高于基于扩散和采样的基线；在真实7自由度机械臂上，成功避开每次试验中都会碰撞的部署障碍物。代码与实验视频见https://anonymous.4open.science/w/grace-70BB/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。