Multitask learning poses significant challenges due to the highly multimodal and diverse nature of robot action distributions. However, effectively fitting policies to these complex task distributions is often difficult, and existing monolithic models often underfit the action distribution and lack the flexibility required for efficient adaptation. We introduce a novel modular diffusion policy framework that factorizes complex action distributions into a composition of specialized diffusion models, each capturing a distinct sub-mode of the behavior space for a more effective overall policy. In addition, this modular structure enables flexible policy adaptation to new tasks by adding or fine-tuning components, which inherently mitigates catastrophic forgetting. Empirically, across both simulation and real-world robotic manipulation settings, we illustrate how our method consistently outperforms strong modular and monolithic baselines.

翻译：多任务学习因机器人动作分布的高度多模态和多样性而面临重大挑战。然而，有效拟合策略以适应这些复杂的任务分布通常较为困难，现有的单体模型往往对动作分布欠拟合，且缺乏高效适应所需的灵活性。我们提出一种新颖的模块化扩散策略框架，将复杂的动作分布分解为多个专用扩散模型的组合，每个模型捕获行为空间中的一个独特子模式，从而形成更有效的整体策略。此外，这种模块化结构通过添加或微调组件，实现了对新任务的灵活策略适应，这本质上缓解了灾难性遗忘问题。通过仿真和真实世界机器人操作场景的实证研究，我们展示了该方法如何持续优于强大的模块化和单体基线模型。