GPLAC: Generalizing Vision-Based Robotic Skills using Weakly Labeled Images

by   Avi Singh, et al.

We tackle the problem of learning robotic sensorimotor control policies that can generalize to visually diverse and unseen environments. Achieving broad generalization typically requires large datasets, which are difficult to obtain for task-specific interactive processes such as reinforcement learning or learning from demonstration. However, much of the visual diversity in the world can be captured through passively collected datasets of images or videos. In our method, which we refer to as GPLAC (Generalized Policy Learning with Attentional Classifier), we use both interaction data and weakly labeled image data to augment the generalization capacity of sensorimotor policies. Our method combines multitask learning on action selection and an auxiliary binary classification objective, together with a convolutional neural network architecture that uses an attentional mechanism to avoid distractors. We show that pairing interaction data from just a single environment with a diverse dataset of weakly labeled data results in greatly improved generalization to unseen environments, and show that this generalization depends on both the auxiliary objective and the attentional architecture that we propose. We demonstrate our results in both simulation and on a real robotic manipulator, and demonstrate substantial improvement over standard convolutional architectures and domain adaptation methods.



There are no comments yet.


page 1

page 4

page 6

page 8

page 11

page 12


Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos

We are motivated by the goal of generalist robots that can complete a wi...

Domain2Vec: Deep Domain Generalization

We address the problem of domain generalization where a decision functio...

Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes

We study the problem of robotic stacking with objects of complex geometr...

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

We consider the problem of learning useful robotic skills from previousl...

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

Reinforcement learning is a powerful framework for robots to acquire ski...

RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real

Deep neural network based reinforcement learning (RL) can learn appropri...

Recognizing bird species in diverse soundscapes under weak supervision

We present a robust classification approach for avian vocalization in co...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.