Department of Telecooperation, Johannes Kepler University, Altenberger Strasse 69, 4040 Linz, Austria.
Sensors (Basel). 2019 Mar 20;19(6):1379. doi: 10.3390/s19061379.
Drones are expected to operate autonomously, yet they will also interact with humans to solve tasks together. To support civilian human-drone teams, we propose a distributed architecture where sophisticated operations such as image recognition, coordination with humans, and flight-control decisions are made, not on-board the drone, but remotely. The benefits of such an architecture are the increased computational power available for image recognition and the possibility to integrate interfaces for humans. On the downside, communication is necessary, resulting in the delayed reception of commands. In this article, we discuss the design considerations of the distributed approach, a sample implementation on a smartphone, and an application to the concrete use case of bookshelf inventory. Further, we report experimentally-derived first insights into messaging and command response delays with a custom drone connected through Wi-Fi.
无人机预计将实现自主运行，但它们也将与人类进行交互，共同完成任务。为了支持民用的人机协作团队，我们提出了一种分布式架构，其中复杂的操作，如图像识别、与人类的协调以及飞行控制决策，不是在无人机上进行，而是远程进行。这种架构的好处是，可用于图像识别的计算能力得到了增强，并且可以集成人类接口。不利的一面是，需要进行通信，从而导致命令的接收延迟。在本文中，我们讨论了分布式方法的设计考虑因素、在智能手机上的示例实现，以及对书架库存这一具体用例的应用。此外，我们还通过连接 Wi-Fi 的定制无人机，从实验中获得了有关消息传递和命令响应延迟的初步见解。
