activity
20182020
most citedImitation Learning for High Precision Peg-in-Hole Tasks

18 citations · 46 across the 13 of their papers we have counts for

collaborators

16 papers

cs.LG2020

Stochastic Action Prediction for Imitation Learning

Sagar Gubbi Venkatesh, Nihesh Rathod, Shishir Kolathaya +1

Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. When performing demonstra…

cs.CV2020

Scene Text Detection for Augmented Reality -- Character Bigram Approach to reduce False Positive Rate

Sagar Gubbi, Bharadwaj Amrutur

Natural scene text detection is an important aspect of scene understanding and could be a useful tool in building engaging augmented reality applications. In this work, we address…

cs.RO2020

Multi-Instance Aware Localization for End-to-End Imitation Learning

Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1

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…

cs.RO202018 cited

Imitation Learning for High Precision Peg-in-Hole Tasks

Sagar Gubbi, Shishir Kolathaya, Bharadwaj Amrutur

Industrial robot manipulators are not able to match the precision and speed with which humans are able to execute contact rich tasks even to this day. Therefore, as a means overcom…

cs.CV202010 cited

One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks

Sagar Gubbi Venkatesh, Bharadwaj Amrutur

A robot that can operate in novel and unstructured environments must be capable of recognizing new, previously unseen, objects. In this work, a visual cue is used to specify a nove…

cs.RO20205 cited

Teaching Robots Novel Objects by Pointing at Them

Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1

Robots that must operate in novel environments and collaborate with humans must be capable of acquiring new knowledge from human experts during operation. We propose teaching a rob…