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：离线决策中通过扩散模型生成的轨迹往往与系统动态不匹配，限制了其控制可靠性。我们提出模型预测扩散器（MPDiffuser），这是一种组合扩散框架，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态可行的轨迹。MPDiffuser在采样过程中交织规划器与动力学更新，逐步修正可行性同时保留任务意图。随后通过轻量级排序模块选择最符合任务目标的轨迹。这种组合设计通过使动力学模型能够独立于规划器利用多样化和未见过的数据，提高了样本效率和适应性。实验结果表明，我们在无约束（D4RL）和约束（DSRL）基准测试中相比先前基于扩散的方法取得了一致改进，并通过在真实四足机器人上的部署验证了实用性。