Real-time multi-fusion perceptron architecture for autonomous drones

Abstract

In this paper, a multi-fusion perceptron architecture and real-time algorithms are proposed for AMR (Autonomous Mobile Robot). Traditionally, AGV (Automated Guided Vehicle) has been used in a large number of indoor logistics warehousing, factory automation, and thus, the corresponding sensor environment must be deployed. AMR needs to have various functions, like autonomous navigation, intelligent control, intelligent visual positioning, intelligent detection, etc., to automatically work in different conditions for traditional required fields. In a factory, there are several modes of operations, multi-machine cooperation, heterogeneous machine cooperation, This paper discusses unmanned machines with sensor elements to collaborate and to establish the complementary spatial information lacking in 3D unmanned carriers. A factory-validated multi-aware fusion of small drones is constructed, and a framework with front-end and back-end design is used for multi-computer communication, information analysis, and decentralized collaborative computing. The whole multi-fusion sensor serial platform is proposed and the system consists of a Logitech C270 USB interface Camera, the V4L2 (Video4Linux) universal driver protocol for communication, and a YDLIDAR G4 laser device serial connection. Through the UART communication interface and microcontroller platform, package information exchange and establish the underlying sensor information acquisition with Ethernet/Wi-Fi for remote sensing, algorithm verification, and real-time image confirmation.