基于增强现实的多视图机器人控制系统

A Tele-operation System of Multi-view Robot Based on Augmented Reality

传统的基于增强现实的单视图视频融合机器人控制系统存在如下问题:场景深度信息不足;标识被遮挡等导致标识识别失败,从而影响视频融合;视频传输过程中由网络拥塞造成的时延丢包,影响反馈视频的实时高质量地显示。为此,提出了多视图视频融合方法,构建多视图控制系统,并提出了改进的网络拥塞控制策略。实验结果表明,控制系统能有效地提高叠加显示仿真机器人的稳定性,很大程度上提高了操作的正确率。

In traditional robot control system of single-view based on Augmented Reality, the following problems can seriously affect the overall performance of the system: insufficient depth information, failure in overlap of robot model video to real robot video due to hidden mark, and bad quality of video results from a congested network. To solve the mentioned problems, this paper proposes a robot control system of multi-view based on augmented reality. A refined network congestion control policy is also presented. Experimental results show that compare with traditional system, system is more stable in video overlap and improve accuracy of user operation.