Paper Info
Title
Q-Attention: Enabling Efficient Learning for Vision-Based Robotic Manipulation
Abstract
Y Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks. This is partly due to the fact that reinforcement learning algorithms are notoriously difficult and time consuming to train, which is exacerbated when training from images rather than full-state inputs. As humans perform manipulation tasks, our eyes closely monitor every step of the process with our gaze focusing sequentially on the objects being manipulated. With this in mind, we present our Attention-driven Robotic Manipulation (ARM) algorithm, which is a general manipulation algorithm that can be applied to a range of sparse-rewarded tasks, given only a small number of demonstrations. ARM splits the complex task of manipulation into a 3 stage pipeline: (1) a Q-attention agent extracts relevant pixel locations from RGB and point cloud inputs, (2) a next-best pose agent that accepts crops from the Q-attention agent and outputs poses, and (3) a control agent that takes the goal pose and outputs joint actions. We show that current learning algorithms fail on a range of RLBench tasks, whilst ARM is successful. Videos found at: https://sites.google.com/view/q-attention.
Year
DOI
Venue
2022
10.1109/LRA.2022.3140817
IEEE ROBOTICS AND AUTOMATION LETTERS
Keywords
DocType
Volume
Deep learning in grasping and manipulation, learning from demonstration, reinforcement learning
Journal
7
Issue
ISSN
Citations 
2
2377-3766
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Stephen James1586.02
Andrew J. Davison26707350.85