UprightRL: Upright Orientation Estimation of 3D Shapes via Reinforcement Learning
Loading...
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
In this paper, we study the problem of 3D shape upright orientation estimation from the perspective of reinforcement learning, i.e. we teach a machine (agent) to orientate 3D shapes step by step to upright given its current observation. Unlike previous methods, we take this problem as a sequential decision-making process instead of a strong supervised learning problem. To achieve this, we propose UprightRL, a deep network architecture designed for upright orientation estimation. UprightRL mainly consists of two submodules: an Actor module and a Critic module which can be learned with a reinforcement learning manner. Specifically, the Actor module selects an action from the action space to perform a point cloud transformation and obtain the new point cloud for the next environment state, while the Critic module evaluates the strategy and guides the Actor to choose the next stage action. Moreover, we design a reward function that encourages the agent to select action which is conducive to orient model towards upright orientation with a positive reward and negative otherwise. We conducted extensive experiments to demonstrate the effectiveness of the proposed model, and experimental results show that our network outperforms the stateof- the-art. We also apply our method to the robot grasping-and-placing experiment, to reveal the practicability of our method.
Description
@article{10.1111:cgf.14419,
journal = {Computer Graphics Forum},
title = {{UprightRL: Upright Orientation Estimation of 3D Shapes via Reinforcement Learning}},
author = {Chen, Luanmin and Xu, Juzhan and Wang, Chuan and Huang, Haibin and Huang, Hui and Hu, Ruizhen},
year = {2021},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14419}
}