A Appendix

We show different kinds of perturbations in our benchmarks in Fig.5. We show more image samples of unseen perturbations in Figure 1. We use "snow", "frost", "fog" (left to We also show the comparison when choosing different basis perturbations in Table. 5. The final set we used are better than other sets (e.g., V channel only, or V channel + B channel + Blur) on Notice we don't compare them on single perturbation and The resulting dataset contains approximately 10,000 images. All of them are then randomly split into training/validation/test data with an approximate ratio 20:1:2. There are several good autonomous driving datasets, but not all of them are suitable for the end-to-end learning to steer task.