当前位置: X-MOL 学术Int. J. Intell. Robot. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Robot grasping in dense clutter via view-based experience transfer
International Journal of Intelligent Robotics and Applications ( IF 2.1 ) Pub Date : 2021-05-28 , DOI: 10.1007/s41315-021-00179-y
Jen-Wei Wang , Chia-Lien Li , Jian-Lun Chen , Jyh-Jone Lee

To perform object grasping in dense clutter, we propose a novel algorithm for grasp detection. To obtain grasp candidates, we developed instance segmentation and view-based experience transfer as part of the algorithm. Subsequently, we established an algorithm for collision avoidance and stability analysis to determine the optimal grasp for robot grasping. The strategy for the view-based experience transfer was to first find the object view and then transfer the grasp experience onto the clutter scenario. This strategy has two advantages over existing learning-based methods for finding grasp candidates. (1) our approach can effectively exclude the influence of noise or occlusion on images and precisely detect grasps that are well aligned on each target object. (2) our approach can efficiently find out optimal grasps on each target object and has the flexibility of adjusting and redefining the grasp experience based on the type of target object. We evaluated our approach using some open-source datasets and with a real-world robot experiment, which involved a six-axis robot arm with a two-jaw parallel gripper and a Kinect V2 RGB-D camera. The experimental results show that our proposed approach can be generalized to objects with complex shape, and is able to grasp on dense clutter scenarios where different types of objects are in a bin. To demonstrate our grasping pipeline, a video is provided at https://youtu.be/gQ3SO6vtTpA.



中文翻译:

机器人通过基于视图的经验转移抓取密集杂物

为了在密集的杂波中执行目标抓取,我们提出了一种新颖的抓取检测算法。为了获得候选对象,我们开发了实例分割和基于视图的经验转移作为算法的一部分。随后,我们建立了碰撞避免和稳定性分析算法,以确定机器人抓取的最佳抓取方式。基于视图的经验转移的策略是首先找到对象视图,然后将抓取经验转移到杂乱场景中。与现有的基于学习的方法相比,该策略具有两个优势,用于寻找抓手候选者。(1)我们的方法可以有效排除噪声或遮挡对图像的影响,并精确检测每个目标对象上对齐良好的抓取。(2)我们的方法可以有效地找出对每个目标对象的最佳抓握,并且具有根据目标对象的类型调整和重新定义抓握体验的灵活性。我们使用一些开源数据集和真实世界的机器人实验来评估我们的方法,其中包括一个带有两爪平行抓手和 Kinect V2 RGB-D 相机的六轴机器人手臂。实验结果表明,我们提出的方法可以推广到具有复杂形状的物体,并且能够掌握不同类型物体在垃圾箱中的密集杂波场景。为了演示我们的抓取流程,https://youtu.be/gQ3SO6vtTpA 提供了一个视频。我们使用一些开源数据集和真实世界的机器人实验来评估我们的方法,其中包括一个带有两爪平行抓手和 Kinect V2 RGB-D 相机的六轴机器人手臂。实验结果表明,我们提出的方法可以推广到具有复杂形状的物体,并且能够掌握不同类型物体在垃圾箱中的密集杂波场景。为了演示我们的抓取流程,https://youtu.be/gQ3SO6vtTpA 提供了一个视频。我们使用一些开源数据集和一个真实世界的机器人实验对我们的方法进行了评估,该实验涉及一个六轴机器人手臂,一个两爪平行夹具和一个Kinect V2 RGB-D相机。实验结果表明,我们提出的方法可以推广到具有复杂形状的物体,并且能够掌握不同类型物体在垃圾箱中的密集杂波场景。为了演示我们的抓取流程,https://youtu.be/gQ3SO6vtTpA 提供了一个视频。

更新日期:2021-05-28
down
wechat
bug