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.

翻译：抓取是机器人学中长期面临的关键且具有挑战性的问题。其中最重要的挑战之一是如何使抓取在非结构化环境中对新物体及不同夹爪具有泛化性和鲁棒性。我们提出了 \regnet，一种能够适配不同平行夹爪以抓取多样化物体的机器人抓取系统。为支持不同夹爪，\regnet 将夹爪参数嵌入点云，并基于此预测合适的抓取构型。该系统包含三个组件：评分网络（SN）、抓取区域网络（GRN）和优化网络（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，基于所选点，GRN 生成一组抓取提案。最后，RN 对抓取提案进行优化，以获得更精确、更鲁棒的预测。我们设计了一种分析策略，用于从预测的抓取集合中选择最优抓取执行。为训练 \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生成的无碰撞抓取构型。实验结果表明，采用分析策略的 \regnet 在包含 $20$ 个物体的真实杂乱场景中取得了 $74.98\%$ 的最高成功率，显著优于包括 GPD、PointNetGPD 和 S4G 在内的多种先进方法。代码与数据集发布于 https://github.com/zhaobinglei/REGNet-V2。