Offline decision-making via diffusion models often produces trajectories that are misaligned with system dynamics, limiting their reliability for control. We propose Model Predictive Diffuser (MPDiffuser), a compositional diffusion framework that combines a diffusion planner with a dynamics diffusion model to generate task-aligned and dynamically plausible trajectories. MPDiffuser interleaves planner and dynamics updates during sampling, progressively correcting feasibility while preserving task intent. A lightweight ranking module then selects trajectories that best satisfy task objectives. The compositional design improves sample efficiency and adaptability by enabling the dynamics model to leverage diverse and previously unseen data independently of the planner. Empirically, we demonstrate consistent improvements over prior diffusion-based methods on unconstrained (D4RL) and constrained (DSRL) benchmarks, and validate practicality through deployment on a real quadrupedal robot.

翻译：通过扩散模型进行离线决策时，常会产生与系统动力学不一致的轨迹，这限制了其在控制应用中的可靠性。我们提出了模型预测扩散器（MPDiffuser），这是一种组合式扩散框架，它将扩散规划器与动力学扩散模型相结合，以生成任务对齐且动力学合理的轨迹。MPDiffuser在采样过程中交替进行规划器更新与动力学更新，在保持任务意图的同时逐步修正可行性。随后，一个轻量级的排序模块会选择最能满足任务目标的轨迹。这种组合式设计通过使动力学模型能够独立于规划器利用多样化的、先前未见过的数据，从而提高了采样效率和适应性。实证结果表明，在无约束（D4RL）和带约束（DSRL）基准测试中，我们的方法相较于先前的基于扩散的方法取得了持续改进，并通过在真实四足机器人上的部署验证了其实用性。