Learning Goal-Oriented Non-Prehensile Pushing in Cluttered Scenes

Nils Dengler

TL;DR: A deep reinforcement learning approach to push objects in cluttered tabletop scenes in a contact rich manner

Abstract:

Pushing objects through cluttered scenes is a
challenging task, especially when the objects to be pushed have
initially unknown dynamics and touching other entities has to
be avoided to reduce the risk of damage. In this paper, we
approach this problem by applying deep reinforcement learning
to generate pushing actions for a robotic manipulator acting
on a planar surface where objects have to be pushed to goal
locations while avoiding other items in the same workspace.
With the latent space learned from a depth image of the scene
and other observations of the environment, such as contact
information between the end effector and the object as well as
distance to the goal, our framework is able to learn contact-rich
pushing actions that avoid collisions with other objects. As the
experimental results with a six degrees of freedom robotic arm
show, our system is able to successfully push objects from start
to end positions while avoiding nearby objects. Furthermore, we
evaluate our learned policy in comparison to a state-of-the-art
pushing controller for mobile robots and show that our agent
performs better in terms of success rate, collisions with other
objects, and continuous object contact in various scenarios.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2203.02389/code)