地下埋設物点検用屋外移動ロボットの長距離自己位置推高精度化手法の検証

抄録

The number of infrastructure facilities in Japan that require inspection is expected to increase rapidly in the future. In addition, currently, infrastructure equipment inspections are performed manually, but the decrease in the number of inspection workers is also a problem. In particular, hand-push measuring trolleys equipped with underground radar are used for inspection work on underground infrastructure equipment, but this requires a great deal of labor and time, so the introduction of robots is required to improve efficiency and save manpower. It is being done. When robots perform inspection work on underground infrastructure equipment, they may be required to travel long distances of several tens of meters or more, and highly accurate self-position estimation is required for autonomous movement. In this study, we investigated a method to calculate the absolute coordinate position of a robot from the color information and depth information of the four corner points of an AR marker using an RGB-D sensor.