Investigation of Factorized Optical Flows as Mid-Level Representations
arXiv:2203.04927 · doi:10.1109/IROS47612.2022.9981638
Abstract
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.
arXiv commentTing-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang, and Shan-Ya Yang contributed equally to this work, names listed in alphabetical order; This work has been submitted to the IEEE for possible publication
References in corpus (15)
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- End to End Learning for Self-Driving Cars
- Soft Actor-Critic Algorithms and Applications
- End-to-End Training of Deep Visuomotor Policies
- Deep Reinforcement Learning framework for Autonomous Driving
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Unity: A General Platform for Intelligent Agents
- A Review on Deep Learning in UAV Remote Sensing
- Soft Actor-Critic for Discrete Action Settings
- Driving Policy Transfer via Modularity and Abstraction
- Does computer vision matter for action?
- Discrete and Continuous Action Representation for Practical RL in Video Games
- Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
- Motion Perception in Reinforcement Learning with Dynamic Objects
- Flow-based Intrinsic Curiosity Module