Great success has been achieved in the 6-DoF grasp learning from the point cloud input, yet the computational cost due to the point set orderlessness remains a concern. Alternatively, we explore the grasp generation from the RGB-D input in this paper. The proposed solution, Keypoint-GraspNet, detects the projection of the gripper keypoints in the image space and then recover the SE(3) poses with a PnP algorithm. A synthetic dataset based on the primitive shape and the grasp family is constructed to examine our idea. Metric-based evaluation reveals that our method outperforms the baselines in terms of the grasp proposal accuracy, diversity, and the time cost. Finally, robot experiments show high success rate, demonstrating the potential of the idea in the real-world applications.
翻译：从点云输入中学习的6-DoF抓取方法取得了巨大成功,然而,由于点定无秩序造成的计算成本仍然令人关切。 或者,我们探索本文中RGB-D输入的抓取生成方法。 提议的解决方案“ Keypoint-GraspNet ” 检测图像空间中抓取关键点的预测,然后用PnP算法来恢复SE(3) 。 以原始形状和抓取家庭为基础的合成数据集是用来检查我们的想法的。 以矩阵为基础的评估显示,我们的方法在抓取建议准确性、多样性和时间成本方面超过了基线。 最后,机器人实验显示高成功率,展示了这个想法在现实世界应用中的潜力。
相关内容
微信扫码咨询专知VIP会员