Mr. Yuto Tsuchiya mainly conducts this research. ]

In this project, we consider household robots that pour various contents from deformable containers. Such pouring is often seen in cooking and refilling. To achieve this kind of pouring, we reduce the deformation of the container during pouring and thus carefully design the grasping strategy: the palm of one hand supports the deformable container from the bottom and the other hand pulls up the container from the top. We apply the proposed system to pouring four different kinds of contents: breakfast cereal, coffee beans, flour, and rice. The experiment verifies that the proposed system successfully pours the four contents. To evaluate the system quantitatively, we measure 1) the deformation of the container using a motion capture system and 2) the success rate of pouring. We verify that the dual-arm pouring reduced the deformation by 66% compared to a single-arm motion and that the success rate is greater than 90%.

Reference

1. Y. Tsuchiya, T. Kiyokawa, G. A. Garcia R., J. Takamatsu, and T. Ogasawara, “Pouring from Deformable Containers Based on Tactile Information Using a Dual-Arm Robot”, International Journal of Robotic Computing, vol. 1, no. 2, 2019. [Link]