Investigation of Factorized Optical Flows as Mid-Level Representations
This work addresses a specific bottleneck in modular robotic frameworks, offering an incremental improvement through a configurable analysis framework.
The paper tackles the problem of bridging perception and control in modular robotic learning by introducing factorized optical flow maps as mid-level representations, reporting experimental results across four environments with static and dynamic objects to validate their effectiveness.
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.