Saved in:
Bibliographic Details
Main Authors: Yang, Hsuan-Kung, Hsiao, Tsu-Ching, Liao, Ting-Hsuan, Liu, Hsu-Shen, Tsao, Li-Yuan, Wang, Tzu-Wen, Yang, Shan-Ya, Chen, Yu-Wen, Liao, Huang-Ru, Lee, Chun-Yi
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2203.04927
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912086353772544
author Yang, Hsuan-Kung
Hsiao, Tsu-Ching
Liao, Ting-Hsuan
Liu, Hsu-Shen
Tsao, Li-Yuan
Wang, Tzu-Wen
Yang, Shan-Ya
Chen, Yu-Wen
Liao, Huang-Ru
Lee, Chun-Yi
author_facet Yang, Hsuan-Kung
Hsiao, Tsu-Ching
Liao, Ting-Hsuan
Liu, Hsu-Shen
Tsao, Li-Yuan
Wang, Tzu-Wen
Yang, Shan-Ya
Chen, Yu-Wen
Liao, Huang-Ru
Lee, Chun-Yi
contents In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks. To investigate the advantages of factorized flow maps and examine their interplay with the other types of mid-level representations, we further develop a configurable framework, along with four different environments that contain both static and dynamic objects, for analyzing the impacts of factorized optical flow maps on the performance of deep reinforcement learning agents. Based on this framework, we report our experimental results on various scenarios, and offer a set of analyses to justify our hypothesis. Finally, we validate flow factorization in real world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2203_04927
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Investigation of Factorized Optical Flows as Mid-Level Representations
Yang, Hsuan-Kung
Hsiao, Tsu-Ching
Liao, Ting-Hsuan
Liu, Hsu-Shen
Tsao, Li-Yuan
Wang, Tzu-Wen
Yang, Shan-Ya
Chen, Yu-Wen
Liao, Huang-Ru
Lee, Chun-Yi
Machine Learning
Artificial Intelligence
In this paper, we introduce a new concept of incorporating factorized flow maps as mid-level representations, for bridging the perception and the control modules in modular learning based robotic frameworks. To investigate the advantages of factorized flow maps and examine their interplay with the other types of mid-level representations, we further develop a configurable framework, along with four different environments that contain both static and dynamic objects, for analyzing the impacts of factorized optical flow maps on the performance of deep reinforcement learning agents. Based on this framework, we report our experimental results on various scenarios, and offer a set of analyses to justify our hypothesis. Finally, we validate flow factorization in real world scenarios.
title Investigation of Factorized Optical Flows as Mid-Level Representations
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2203.04927