Raise One and Infer Three: Toward Reasoning- and Memory-Augmented Diffusion Policy Generalization

摘要

Diffusion policy has shown impressive performance in robotic manipulation tasks while struggling with out-of-distribution shifts and limited demonstrations. Recent advances primarily focus on improving geometric or perceptual representations for diffusion policy. However, these approaches rely heavily on instantaneous observations, making them vulnerable when visual inputs deviate from the training distribution. Our key insight is that robust generalization in diffusion policy requires both structured reasoning over skill compositions and an explicit memory mechanism for accumulating and reusing learned policy knowledge. To this end, we propose "raise one and infer three" diffusion policy (ROITDP), a novel approach that introduces two complementary mechanisms. First, we propose a reasoning mechanism built upon the Chain-of-Skill Noise Watermark, which encodes skill-level reasoning graph representations into the initial noise space, thereby enabling temporally coherent multi-step reasoning throughout the diffusion process under distribution shifts. We further introduce a memory mechanism in the form of a Self-evolving Policy Knowledge Bank that discretizes spatio-temporally refined trajectories into reusable skill primitives via a VQ-VAE architecture, providing adaptive memory to guide and refine action generation. Extensive experimental results on both simulated and real-world environments demonstrate the superiority and robustness of our method.