RFusion: Robotic Grasping via RF-Visual Sensing and Learning
RFusion: Robotic Grasping via RF-Visual Sensing and Learning
复制标题
DOI：
10.1145/3485730.3485944
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Tara Boroushaki;I. Perper;Mergen Nachin;Alberto Rodriguez;Fadel M. Adib
中科院分区：
文献类型：
--
作者：
Tara Boroushaki;I. Perper;Mergen Nachin;Alberto Rodriguez;Fadel M. Adib
我们介绍 RFusion 的设计、实现和评估，这是一个机器人系统，可以在视线、非视线和完全遮挡的环境中搜索和检索带有 RFID 标签的物品。 RFusion 由一个机械臂组成，机械臂的夹具上绑有一个摄像头和天线。我们的设计引入了两项关键创新：第一个是一种在几何上融合射频和视觉信息的方法，以减少目标物体位置的不确定性，即使该物体完全被遮挡也是如此。第二个是一种新颖的强化学习网络，它使用融合的射频视觉信息来有效地定位、操纵和抓取目标物品。我们构建了 RFusion 的端到端原型，并在具有挑战性的现实环境中对其进行了测试。我们的评估表明，RFusion 能够以厘米级精度定位目标项目，并且在检索完全被遮挡的物体时实现 96% 的成功率，即使它们位于一堆物体下面。该系统为仓库、制造工厂和智能家居等复杂环境中的新型机器人检索任务铺平了道路。
We present the design, implementation, and evaluation of RFusion, a robotic system that can search for and retrieve RFID-tagged items in line-of-sight, non-line-of-sight, and fully-occluded settings. RFusion consists of a robotic arm that has a camera and antenna strapped around its gripper. Our design introduces two key innovations: the first is a method that geometrically fuses RF and visual information to reduce uncertainty about the target object's location, even when the item is fully occluded. The second is a novel reinforcement-learning network that uses the fused RF-visual information to efficiently localize, maneuver toward, and grasp target items. We built an end-to-end prototype of RFusion and tested it in challenging real-world environments. Our evaluation demonstrates that RFusion localizes target items with centimeter-scale accuracy and achieves 96% success rate in retrieving fully occluded objects, even if they are under a pile. The system paves the way for novel robotic retrieval tasks in complex environments such as warehouses, manufacturing plants, and smart homes.