Hybrid Sensor-Based and Frontier-Based Exploration Algorithm for Autonomous Transport Vehicle Map Generation

In this paper, we present a method of effectively creating environment maps on an auto-transport system in logistics and industrial site management applications, e.g., an automobile assembly plant. The key objective of the study is creating a map effectively. Simultaneous Localization and Mapping (SLAM) is established as a general map-generating method. The map is, however, created with ad hoc and manual. Thus, an exploration method in an unknown environment for autonomously generating a map has been studied for decades. The main method is frontier-based exploration. This method presents a problem for an efficient mapping method in a wide environment, and for accuracy of the map depending on the local area. In the backgrounds, an autonomous exploration algorithm using only infrared sensor and odometer information from a robot is proposed as a sensor-based exploration approach without using map information. The proposed method requires only a depth sensor and camera on a robot. Next, we propose a hybrid exploration to decrease unavailable areas in frontier-based exploration. To perform our proposed method, an environment map is created by a mobile robot, and the effectiveness of the hybrid exploration method is demonstrated.