期刊
APPLIED SCIENCES-BASEL
卷 11, 期 22, 页码 -出版社
MDPI
DOI: 10.3390/app112210595
关键词
unmanned aerial vehicle; deep reinforcement learning; visual active tracking
类别
资金
- National Natural Science Foundation (NSF) of China [61976014]
Active tracking control is crucial for UAVs in GPS-denied environments, and this paper proposes an end-to-end high-level control method that leverages deep reinforcement learning to map raw images to high-level action commands. By unifying perception and decision-making stages with a novel high-level controller architecture, encoding spatial and temporal features of dynamic targets, and introducing auxiliary segmentation and motion-in-depth losses for denser training signals, the UAVs achieved significantly better performance in active tracking tasks than traditional three-stage methods.
Active tracking control is essential for UAVs to perform autonomous operations in GPS-denied environments. In the active tracking task, UAVs take high-dimensional raw images as input and execute motor actions to actively follow the dynamic target. Most research focuses on three-stage methods, which entail perception first, followed by high-level decision-making based on extracted spatial information of the dynamic target, and then UAV movement control, using a low-level dynamic controller. Perception methods based on deep neural networks are powerful but require considerable effort for manual ground truth labeling. Instead, we unify the perception and decision-making stages using a high-level controller and then leverage deep reinforcement learning to learn the mapping from raw images to the high-level action commands in the V-REP-based environment, where simulation data are infinite and inexpensive. This end-to-end method also has the advantages of a small parameter size and reduced effort requirements for parameter turning in the decision-making stage. The high-level controller, which has a novel architecture, explicitly encodes the spatial and temporal features of the dynamic target. Auxiliary segmentation and motion-in-depth losses are introduced to generate denser training signals for the high-level controller's fast and stable training. The high-level controller and a conventional low-level PID controller constitute our hierarchical active tracking control framework for the UAVs' active tracking task. Simulation experiments show that our controller trained with several augmentation techniques sufficiently generalizes dynamic targets with random appearances and velocities, and achieves significantly better performance, compared with three-stage methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据