In-hand pose estimation with FingerVision
Shintaro Takayama, Akihiko Yamaguchi, Koichi Hashimoto · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2018
FingerVision is an optical multimodal sensor for robot grippers. This sensor is transparent, soft at the surface, covered with dotted-markers material, and a camera is mounted inside. By using this sensor, it is possible to estimate the contact pressure by tracking the markers on the surface, and to acquire the visual information of the nearby object. If object information could be acquired in-hand, it leads to a reduction in cycle time of work and so on. FingerVision has the potential to acquire various information of objects based on visual information. In this research, we propose a method for estimating the in-hand pose of a grasped object in order to present the possibility of acquiring object information with FingerVision.