Multi-Instance Aware Localization for End-to-End Imitation Learning
Sagar Gubbi Venkatesh,Raviteja Upadrashta,Shishir Kolathaya,Bharadwaj Amrutur,Sagar Gubbi Venkatesh,Raviteja Upadrashta,Shishir Kolathaya,Bharadwaj Amrutur
Existing architectures for imitation learning using image-to-action policy networks perform poorly when presented with an input image containing multiple instances of the object of interest, especially when the number of expert demonstrations available for training are limited. We show that end-to-end policy networks can be trained in a sample efficient manner by (a) appending the feature map outp...
