2 0 0 0 物体把持の視覚能力を自動獲得するロボット
2 0 0 0 OA 挟持グリッパをベースとした 混載商品を識別するピッキングロボットの開発
- 著者
- 堂前 幸康 川西 亮輔 白土 浩司 原口 林太郎 藤田 正弘 山内 悠嗣 山下 隆義 藤吉 弘亘 秋月 秀一 橋本 学
- 出版者
- 一般社団法人 日本ロボット学会
- 雑誌
- 日本ロボット学会誌 (ISSN:02891824)
- 巻号頁・発行日
- vol.38, no.1, pp.95-103, 2020 (Released:2020-01-16)
- 参考文献数
- 16
We proposed a picking robot system which is apllicable to various mixed items in shelves. The robot has a two-finger gripper which can change the open width of the finger. To determine the position, the pose and the open width when the gripper pick items, we proposed efficient determination algorithm which is based on a RGBD sensor data. In our experiments, 25 items of Amazon Picking Challenge 2015 can be picked well by our proposed system. In this paper, we describe the system, the algorithms and the experimental results.
- 著者
- 長谷川 昂宏 山内 悠嗣 山下 隆義 藤吉 弘亘 秋月 秀一 橋本 学 堂前 幸康 川西 亮輔
- 出版者
- 一般社団法人 日本ロボット学会
- 雑誌
- 日本ロボット学会誌 (ISSN:02891824)
- 巻号頁・発行日
- vol.36, no.5, pp.349-359, 2018 (Released:2018-07-15)
- 参考文献数
- 27
Automatization for the picking and placing of a variety of objects stored on shelves is a challenging problem for robotic picking systems in distribution warehouses. Here, object recognition using image processing is especially effective at picking and placing a variety of objects. In this study, we propose an efficient method of object recognition based on object grasping position for picking robots. We use a convolutional neural network (CNN) that can achieve highly accurate object recognition. In typical CNN methods for object recognition, objects are recognized by using an image containing picking targets from which object regions suitable for grasping can be detected. However, these methods increase the computational cost because a large number of weight filters are convoluted with the whole image. The proposed method detects all graspable positions from an image as a first step. In the next step, it classifies an optimal grasping position by feeding an image of the local region at the grasping point to the CNN. By recognizing the grasping positions of the objects first, the computational cost is reduced because of the fewer convolutions of the CNN. Experimental results confirmed that the method can achieve highly accurate object recognition while decreasing the computational cost.