【摘要】 随着信息智能化的快速发展,机器人在工作过程中面临着大量的数据计算、存储与调度等问题,结合多机器人协同工作,提出了基于云计算的多机器人目标智能跟随控制方法。通过人机载距传感器对多机器人以及跟踪目标进行定位,建立二维坐标系的局部地图。以目标的运动状态为基础,对其运动方向和速度进行预测,为每个机器人创建独自的跟踪器来预估目标的跟随状态,将最大近似概率和对应的测量数据、跟踪轨迹进行关联,直到所有的测量数据或跟踪轨迹全部关联完毕。采用松散耦合架构的设计方法对云服务平台的基础层进行设计,为了降低云服务系统的复杂性以及耗时性,采用容器批量部署方式的微服务体系,将各个小服务的代码与环境进行隔离。实验结果表明,所提方法不仅实现了多机器人对目标的良好跟踪,还可以通过云操作系统进行任务分配,稳定高效地完成目标智能跟踪与相互协作。更多还原

【Abstract】 With the rapid development of information intelligence, robots are faced with a large number of data calculation, storage and scheduling problems. Combined with multi-robot cooperative work, a multi-robot intelligent tracking control method based on cloud computing is proposed. Firstly, multi robots and tracking targets were located by a human-machine range sensor, and a local map of a two-dimensional coordinate system was established. Then, based on the motion state of the target, the motion direction and speed of the target were predicted, and an independent tracker was created for each robot to predict the following state of the target. The maximum approximate probability was associated with the corresponding measurement data and tracking track until all the measurement data or tracking tracks were all connected. Finally, the basic layer of the cloud service platform was designed by using the design method of loosely coupled architecture. In order to reduce the complexity and time-consuming of the cloud service system, the microservice system of container batch deployment was adopted to isolate the code of each small service from the environment. The experimental results show that the proposed method not only achieves good target tracking of multi robots, but also achieves task allocation through cloud operating system, and achieves target intelligent tracking and mutual cooperation stably and efficiently.更多还原