Robotic Grasping On Cornell Grasp Dataset 1
Métriques
5 fold cross validation
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | 5 fold cross validation | Paper Title | Repository |
|---|---|---|---|
| Fast Search | 60.5 | Deep Learning for Detecting Robotic Grasps | - |
| AlexNet, MultiGrasp | 88 | Real-Time Grasp Detection Using Convolutional Neural Networks | |
| Multi-Modal Grasp Predictor | 89.21 | Robotic Grasp Detection using Deep Convolutional Neural Networks | - |
| grasp_det_seg_cnn (rgb only, IW split) | 98.2 | End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB | |
| ResNet50 multi-grasp predictor | 96 | Real-world multiobject, multigrasp detection | |
| GR-ConvNet | 97.7 | Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network | |
| GGCNN | 73 | Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach |
0 of 7 row(s) selected.