Knowledge Commons of Institute of Automation,CAS
GPR: Grasp Pose Refinement Network for Cluttered Scenes | |
Wei W(韦伟)1,2; Luo YK(罗永康)1; Li FY(李富裕)1,2; Xu GY(许广云)1,2; Zhong J(钟君)1; Li WY(黎万义)1; Wang P(王鹏)1,2 | |
2021-05 | |
会议名称 | IEEE International Conference on Robotics and Automation |
会议日期 | 2021-5-31 |
会议地点 | 中国西安 |
摘要 | Object grasping in cluttered scenes is a widely investigated field of robot manipulation. Most of the current works focus on estimating grasp pose from point clouds based on an efficient single-shot grasp detection network. However, due to the lack of geometry awareness of the local grasping area, it may cause severe collisions and unstable grasp configurations. In this paper, we propose a two-stage grasp pose refinement network which detects grasps globally while fine-tuning low-quality grasps and filtering noisy grasps locally. Furthermore, we extend the 6-DoF grasp with an ex- tra dimension as grasp width which is critical for collisionless grasping in cluttered scenes. It takes a single-view point cloud as input and predicts dense and precise grasp configurations. To enhance the generalization ability, we build a synthetic single-object grasp dataset including 150 commodities of various shapes, and a complex multi-object cluttered scene dataset including 100k point clouds with robust, dense grasp poses and mask annotations. Experiments conducted on Yumi IRB-1400 Robot demonstrate that the model trained on our dataset performs well in real environments and outperforms previous methods by a large margin. |
七大方向——子方向分类 | 智能机器人 |
国重实验室规划方向分类 | 实体人工智能系统决策-控制 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/54590 |
专题 | 中国科学院自动化研究所 |
作者单位 | 1.中科院自动化所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wei W,Luo YK,Li FY,et al. GPR: Grasp Pose Refinement Network for Cluttered Scenes[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
GPR_Grasp_Pose_Refin(4288KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论