Deictic Image Maps: An Abstraction For Learning Pose Invariant Manipulation Policies

By Robert W. Platt, Colin Kohler, Marcus Gualtieri. 2018

11 citations recorded by the source corpus.

In applications of deep reinforcement learning to robotics, it is often the case that we want to learn pose invariant policies: policies that are invariant to changes in the position and orientation of objects in the world. For example, consider a pegin-hole insertion task. If the agent learns to insert a peg into one hole, we would like that policy to generalize to holes presented in different poses. Unfortunately, this is a challenge using conventional methods. This paper proposes a novel state and action abstraction that is invariant to pose shifts called deictic image maps that can be used with deep reinforcement learning. We provide broad conditions under which optimal abstract policies are optimal for the underlying system. Finally, we show that the method can help solve challenging robotic manipulation problems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Transporter Networks: Rearranging the Visual World for Robotic Manipulation (2020, methodology): “Our method uses 3D reconstruction to project visual data onto a spatiallyconsistent representation as input, with which it is able to better exploit equivariance [13, 14] for inductive biases that are present within the geometric symmetries [15] of the data for more efficient learning.”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “g laser scanner readings), rather than problem-specific features, or a deictic representation [302].”