Equivariant Grasp learning In Real Time
Visual grasp detection is a key problem in robotics where the agent must learn to model the grasp function, a mapping from an image of a scene onto a set of feasible grasp poses. In this paper, we recognize that the grasp function is $\mathrm{SE}(2)$-equivariant and that it can be modeled using an equivariant convolutional neural network. As a result, we are able to significantly improve the sample efficiency of grasp learning to the point where we can learn a good approximation of the grasp function within only 500 grasp experiences. This is fast enough that we can learn to grasp completely on a physical robot in about an hour.
PDF AbstractTasks
Datasets
Add Datasets
introduced or used in this paper
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here
