REGNet V2：用于点云中不同尺寸夹爪的端到端基于区域的抓取检测网络
REGNet V2: End-to-End REgion-based Grasp Detection Network for Grippers of Different Sizes in Point Clouds
AI总结：
本文提出REGNet，一种能适应不同平行夹爪的端到端基于区域的抓取检测系统，通过将夹爪参数嵌入点云并利用三个网络组件预测并精炼抓取配置，在真实杂乱场景中达到74.98%的最高成功率。
摘要：
多年来，抓取一直是机器人领域一个至关重要且具有挑战性的问题。最重要的挑战之一是如何使抓取在非结构化环境中对新颖物体以及夹爪具有泛化性和鲁棒性。我们提出了REGNet，这是一种能够适应不同平行夹爪以抓取多样化物体的机器人抓取系统。为了支持不同的夹爪，REGNet将夹爪参数嵌入到点云中，并基于此预测合适的抓取配置。它包含三个组件：Score Network (SN)、Grasp Region Network (GRN)和Refine Network (RN)。在第一阶段，SN通过抓取置信度分数筛选适合抓取的点。在第二阶段，基于所选的点，GRN生成一组抓取候选。最后，RN对抓取候选进行精炼，以实现更准确和鲁棒的预测。我们设计了一种解析策略，从预测的抓取集合中选择最优抓取予以执行。为了训练REGNet，我们构建了一个大规模抓取数据集，其中包含使用不同平行夹爪的无碰撞抓取配置。实验结果表明，带有解析策略的REGNet在包含20个物体的真实世界杂乱场景中实现了74.98%的最高成功率，显著优于包括GPD、PointNetGPD和S4G在内的几种最先进方法。代码和数据集可在https://github.com/zhaobinglei/REGNet-V2获取。
英文摘要：
Grasping has been a crucial but challenging problem in robotics for many years. One of the most important challenges is how to make grasping generalizable and robust to novel objects as well as grippers in unstructured environments. We present \regnet, a robotic grasping system that can adapt to different parallel jaws to grasp diversified objects. To support different grippers, \regnet embeds the gripper parameters into point clouds, based on which it predicts suitable grasp configurations. It includes three components: Score Network (SN), Grasp Region Network (GRN), and Refine Network (RN). In the first stage, SN is used to filter suitable points for grasping by grasp confidence scores. In the second stage, based on the selected points, GRN generates a set of grasp proposals. Finally, RN refines the grasp proposals for more accurate and robust predictions. We devise an analytic policy to choose the optimal grasp to be executed from the predicted grasp set. To train \regnet, we construct a large-scale grasp dataset containing collision-free grasp configurations using different parallel-jaw grippers. The experimental results demonstrate that \regnet with the analytic policy achieves the highest success rate of $74.98\%$ in real-world clutter scenes with $20$ objects, significantly outperforming several state-of-the-art methods, including GPD, PointNetGPD, and S4G. The code and dataset are available at https://github.com/zhaobinglei/REGNet-V2.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
