Realization of Unmanned Vehicle Navigation Considering Density and Pedestrian Flow with Cloud Information

Abstract

Gradually, unmanned vehicles are more popular and seen in some places, such as department stores or supermarkets with many people. In order to integrate into human daily life, they should be able to avoid crowd and follow pedestrian flow as human will do. It is not enough to only follow the shortest path for them.The purpose of this work is to implement a navigation algorithm in the real world that considers the flow and density of people. We use a cloud computer to receive fixed camera images, divide regions on the image, and then obtain pedestrian flow and density information through FairMOT[2] algorithm, and wirelessly transmit the information to the unmanned vehicle. Therefore, the unmanned vehicle can avoid high density or reverse flow, and better follow social etiquette.In our implementation, flow directions are with different colors, and shown in our experiments. Furthermore, the flow and density information is passed through WiFi, and affects the cost of a new created cost map layer, called people flow and density layer. The density information affects the navigation reliably. Due to the same area may have different directions of people flow, the following flow algorithm is more challenging.The fixed camera we used is a low-cost webcam, and the unmanned vehicle is with a single camera and a one-line lidar.