A Study on the Making Indoor Topology Map for the Autonomous Driving of Wearable Robots

Abstract

When walking with a wearable robot, we may not react properly to the surrounding environment. Therefore, we need to help the wearable robot to walk correctly by providing information of the surrounding environment in the indoor space. SLAM creates a map while the robot moves in real time, so you can use the same map as the actual structure, but it takes a lot of time to create the map. We produce a topology map using the floor plan image. Since the floor plan is produced when a building is made, it is very similar to the actual structure of the building and it is very efficient in terms of time because it does not need to create a map in real-time. In addition, since we generate our topology map using the sensor nodes installed in the building, it matches the coordinates on the floor plan one to one so that the path can be set more accurately and we can find doors, stairs, and obstacles more easily found through object detection. In this study, create a topology map based on a floor plan so that a wearable robot can walk more stably and autonomously, and we can provide the information of object detection by learning a dataset of rooms, doors, and stairs. By synthesizing this information, we transmit it to the wearable robot and provide a path to progress. Conduct an experiment to detect obstacles in the path and transmit the information to wearable robots to prevent accidents.