No abstract

Object manipulation automation in logistic warehouses has recently been actively researched. However, shelf replenishment is a challenge that requires the precise and careful handling of densely piled objects. The irregular arrangement of objects on a shelf makes this task particularly difficult. This paper presents an approach for generating a safe replenishment process from a single depth image, which is provided as an input to two networks to identify arrangement patterns and predict the occurrence of collapsing objects. The proposed inference-based strategy provides an appropriate decision and course of action on whether to create an insertion space while considering the safety of the shelf content. In particular, we exploit the bimanual dexterous manipulation capabilities of the associated robot to resolve the task safely, without re-organizing the entire shelf. Experiments with a real bimanual robot were performed in three typical scenarios: shelved, stacked, and random. The objects were randomly placed in each scenario. The experimental results verify the performance of our proposed method in randomized situations on a shelf with a real bimanual robot.

Synergy is the method that reduces the control inputs of a multi-fingered hand and is utilized for designing underactuated robotic hands and efficient control. Calculating conventional synergies depends on the measured human grasping postures. Therefore, preparing synergies for the not-human-like multi-fingered hands is challenging. We propose a reinforcement learning platform for acquiring synergies of a multi-fingered robotic hand through learning a grasping task. The learning process automatically generates postures for creating synergies so that this system can prepare synergies for any robotic hand. Experiments show that this reinforcement learning platform improves learning tasks and acquires the synergy that is suitable for the learned task.

In this paper, we propose a novel robotic action/observation planning method for playing Yamakuzushi game which is a Japanese board game selecting one Shogi piece from the randomly stacked pile and sliding it off the board. In our proposed method, we first select one of the pieces from the pile by referring a human operation characteristics. We use the CNN trained by using the depth image of the pile and the result of human operation. To successfully slide the selected piece off the board without making collision with the neighboring pieces, we formulate the action/observation planning based on the partially observable Markov decision process (POMDP). We select the view pose to obtain enough visibility of the pile around the selected piece. After obtaining the visibility, we determine the direction of piece's motion to avoid the contact with the neighboring objects. The effectiveness of the proposed method is confirmed by experiments.