Predictive models have been at the core of many robotic systems, from
quadrotors to walking robots. However, it has been challenging to develop and
apply such models to practical robotic manipulation due to high-dimensional
sensory observations such as images. Previous approaches to learning models in
the context of robotic manipulation have either learned whole image dynamics or
used autoencoders to learn dynamics in a low-dimensional latent state. In this
work, we introduce model-based prediction with self-supervised visual
correspondence learning, and show that not only is this indeed possible, but
demonstrate that these types of predictive models show compelling performance
improvements over alternative methods for vision-based RL with autoencoder-type
vision training. Through simulation experiments, we demonstrate that our models
provide better generalization precision, particularly in 3D scenes, scenes
involving occlusion, and in category-generalization. Additionally, we validate
that our method effectively transfers to the real world through hardware
experiments. Videos and supplementary materials available at
this https URL

本文提出基于自监督视觉对应学习的模型预测方法，证明了这种方法能够在视觉学习的强化学习中实现明显的性能提升，并通过模拟实验和硬件实验的验证显示出在一些情境下，这种预测模型具有更好的泛化性能。