Multi-person Collaborative Hoisting Training System Based on Mixed Reality

Abstract

In the early stage of hoisting training, virtual hoisting training equipment is often used to avoid safety accidents caused by lack of experience. However, there are some problems in the existing virtual training equipment, such as single interaction mode, limited viewing angle, and the system that is not portable. To solve the problems, a multi-person cooperative hoisting training system based on mixed reality is proposed in this paper. To ensure the accuracy of the virtual model, on the basis of collecting a large number of actual data, the system employs Pro/E software to carry out 3D accurate modeling of the box hoisting cart. In an effort to ensure the positioning accuracy of the holographic virtual model, the system firstly adopts image recognition method for initial positioning, SLAM algorithm for real-time positioning, and spatial anchor point for accurate positioning. In order to solve the problem of multi-person cooperative training, the system adopts the hardware composition of a server, a plurality of mixed reality intelligent glasses, a wireless router and so on, and uses gesture interaction and wireless analog controller interaction to realize efficient human-machine interaction. Via comparative experiments, it is proved that the system can greatly improve the operation level of operators and is of use value.