Error rate: 8.72
Papers with Code · CC BY-SA 4.0
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.
논문
5 fold cross validation: 97.7
AP_similar: 53.59AP_novel: 24.59AP_seen: 64.45mAP: 47.54
5 fold cross validation: 98.2
AP_similar: 42.27AP_novel: 16.61AP_seen: 47.47mAP: 35.45
5 fold cross validation: 73
AUC: 84.74
5 fold cross validation: 60.5
AP_similar: 61.71AP_novel: 29.75AP_seen: 68.79mAP: 53.42
AP_similar: 54.81AP_novel: 24.31AP_seen: 67.12mAP: 48.75
Accuracy (%): 95.6
Acc: SSS: 99.2%, NSS: 98.8%
5 fold cross validation: 88
5 fold cross validation: 96
AP_similar: 65.21AP_novel: 30.04AP_seen: 72.81mAP: 56.02
5 fold cross validation: 89.21
AP_similar: 58.46AP_novel: 24.63AP_seen: 63.83mAP: 48.97