Towards Monocular Vision based Obstacle Avoidance through Deep Reinforcement Learning
This addresses obstacle avoidance for autonomous robots using only monocular vision, offering an incremental improvement in learning efficiency and transferability.
The paper tackles monocular vision-based obstacle avoidance for autonomous robots by proposing a D3QN method, which achieves twofold learning acceleration compared to a normal deep Q network and successfully transfers from simulation to real robots with generalization to new dynamic environments.
Obstacle avoidance is a fundamental requirement for autonomous robots which operate in, and interact with, the real world. When perception is limited to monocular vision avoiding collision becomes significantly more challenging due to the lack of 3D information. Conventional path planners for obstacle avoidance require tuning a number of parameters and do not have the ability to directly benefit from large datasets and continuous use. In this paper, a dueling architecture based deep double-Q network (D3QN) is proposed for obstacle avoidance, using only monocular RGB vision. Based on the dueling and double-Q mechanisms, D3QN can efficiently learn how to avoid obstacles in a simulator even with very noisy depth information predicted from RGB image. Extensive experiments show that D3QN enables twofold acceleration on learning compared with a normal deep Q network and the models trained solely in virtual environments can be directly transferred to real robots, generalizing well to various new environments with previously unseen dynamic objects.