Robotic Grasping
This task is composed of using Deep Learning to identify how best to grasp objects using robotic arms in different scenarios. This is a very complex task as it might involve dynamic environments and objects unknown to the network.
Papers
Showing 91–100 of 246 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FlexLoG-CD | mAP | 56.02 | — | Unverified |
| 2 | GtG2.0 | mAP | 53.42 | — | Unverified |
| 3 | Scale-Balanced-Grasp-CD | mAP | 48.97 | — | Unverified |
| 4 | graspness-CD | mAP | 48.75 | — | Unverified |
| 5 | HGGD-CD | mAP | 47.54 | — | Unverified |
| 6 | HGGD | mAP | 44.24 | — | Unverified |
| 7 | graspnet-baseline-CD | mAP | 35.45 | — | Unverified |
| 8 | graspnet-baseline | mAP | 21.41 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | grasp_det_seg_cnn (rgb only, IW split) | 5 fold cross validation | 98.2 | — | Unverified |
| 2 | GR-ConvNet | 5 fold cross validation | 97.7 | — | Unverified |
| 3 | ResNet50 multi-grasp predictor | 5 fold cross validation | 96 | — | Unverified |
| 4 | Multi-Modal Grasp Predictor | 5 fold cross validation | 89.21 | — | Unverified |
| 5 | AlexNet, MultiGrasp | 5 fold cross validation | 88 | — | Unverified |
| 6 | GGCNN | 5 fold cross validation | 73 | — | Unverified |
| 7 | Fast Search | 5 fold cross validation | 60.5 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Efficient-Grasping | Accuracy (%) | 95.6 | — | Unverified |
| 2 | GR-ConvNet | Accuracy (%) | 94.6 | — | Unverified |
| 3 | grasp_det_seg_cnn (rgb only) | Accuracy (%) | 92.95 | — | Unverified |