GPGPUを用いたビューベースト教示再生

抄録

View-based approach is one of the methods to obtain environmental information by a camera. This method uses image data itself without models, so it can be applied to manipulation of various objects. In this paper, we studied a robot teaching method using view-based approach: view-based teaching/playback. By using GPGPU, we accelerated a simulation of view-based teaching/playback. We made virtual environments that use images from two viewpoints and that use RGB and range images. In the new environments, we realized both faster processing and more usable images than our previous environment. Lastly, we showed how to pick and place the object by view-based teaching/playback.