Sequence modeling approaches have shown promising results in robot imitation learning. Recently, diffusion models have been adopted for behavioral cloning in a sequence modeling fashion, benefiting from their exceptional capabilities in modeling complex data distributions. The standard diffusion-based policy iteratively generates action sequences from random noise conditioned on the input states. Nonetheless, the model for diffusion policy can be further improved in terms of visual representations. In this work, we propose Crossway Diffusion, a simple yet effective method to enhance diffusion-based visuomotor policy learning via a carefully designed state decoder and an auxiliary self-supervised learning (SSL) objective. The state decoder reconstructs raw image pixels and other state information from the intermediate representations of the reverse diffusion process. The whole model is jointly optimized by the SSL objective and the original diffusion loss. Our experiments demonstrate the effectiveness of Crossway Diffusion in various simulated and real-world robot tasks, confirming its consistent advantages over the standard diffusion-based policy and substantial improvements over the baselines.

翻译：序列建模方法在机器人模仿学习中展现了良好的成果。近年来，扩散模型凭借其在复杂数据分布建模方面的卓越能力，以序列建模的方式被应用于行为克隆。基于扩散的标准策略迭代地从以输入状态为条件的随机噪声中生成动作序列。然而，扩散策略模型在视觉表征方面仍有改进空间。本文提出了一种简单而有效的方法——十字扩散（Crossway Diffusion），通过精心设计的状态解码器和辅助自监督学习目标，增强基于扩散的视觉运动策略学习。状态解码器从反向扩散过程的中间表征中重建原始图像像素及其他状态信息。整个模型通过自监督学习目标和原始扩散损失的联合优化进行训练。实验结果表明，十字扩散在多种模拟和真实机器人任务中具有有效性，证实了其相对于标准扩散策略的持续优势以及相较于基线的显著改进。