Augmenting Imitation Experience via Equivariant Representations
Dhruv Sharma,Alihusein Kuwajerwala,Florian Shkurti,Dhruv Sharma,Alihusein Kuwajerwala,Florian Shkurti
The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data augmentations from computer vision, such as adding random noise to each image, or by synthesizing training images. In this paper we show that there is another pr...
