Host: Japan Society for Fuzzy Theory and Intelligent Informatics
In this paper, we propose a method of learning docking control of autonomous recharging for indoor blimp robot. Indoor blimp robot can fly in a three dimensional space. For this feature, indoor blimp robot might be applied to entertainment flight in an event hall, and searching for human beings in destructive buildings, etc. To achieve these applications, it might be necessary to fly for long term and to trace orbit accurately. There are many researches for tracing orbit for blimp robots, but it is rare to research for long term flight for indoor blimp robot. Indoor blimp robot cannot load heavy battery for flying longer because of payload restriction. To achieve long term flight, one approach is autonomous recharging. We proposed autonomous recharging system in the past papers. But its control does not be enough to accomplish every time recharging. We designed a new control system for blimp robot. This control is based on learning control. We compare a new approach with a past approach. In the end, we conclude that a new approach is suitable for an autonomous recharging for indoor blimp robot.
