Investigation of Factorized Optical Flows as Mid-Level Representations
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 9 Mar 2022.
Builds on
27 of 32 references.
References · 27
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2016OpenAI Gymcited by 1,736
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
- 2016End to End Learning for Self-Driving Carscited by 1,009
- 2015End-to-End Training of Deep Visuomotor Policiescited by 875
- 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
- 2017Reinforcement Learning with Deep Energy-Based Policiescited by 669
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
- 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 316
- 2018Unity: A General Platform for Intelligent Agentscited by 236
- 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 233
15 more
- 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 225
- 2019Soft Actor-Critic for Discrete Action Settingscited by 174
- 2019End-to-End Robotic Reinforcement Learning without Reward Engineeringcited by 122
- 2018Driving Policy Transfer via Modularity and Abstractioncited by 92
- 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
- 2019Does computer vision matter for action?cited by 64
- 2018Representation Flow for Action Recognitioncited by 51
- 2021Learning to See before Learning to Act: Visual Pre-training for Manipulationcited by 51
- 2019Discrete and Continuous Action Representation for Practical RL in Video Gamescited by 39
- 2020Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigationcited by 32
- 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
- 2019Learning to Navigate Using Mid-Level Visual Priorscited by 25
- 2020Optical Flow based Visual Potential Field for Autonomous Drivingcited by 16
- 2019Motion Perception in Reinforcement Learning with Dynamic Objectscited by 13
- 2018Virtual-to-Real: Learning to Control in Visual Semantic Segmentationcited by 12
Built on by
Citing papers per year: 2023: 2.
2 papers.