Open leeivan1007 opened 4 years ago
It is good by 'GQCNN-4.0-PJ' and always can grasp successfully. But it can't predict successfully by 'GQCNN-4.0-SUCTION'.
the depth distance is 0.693m with Q=0.185
there have a point cloud file: https://drive.google.com/file/d/13iyM7MnbWEN_LE1hMO_S_Cwu3fr_XLZC/view?usp=sharing
sampled grasps iter 0
sampled grasps iter 1
sampled grasps iter 2
The original image's surface is smooth. I think maybe it is the cause that suction method can't be successful. Maybe I miss something, but now i don't know what happen clearly...
Think for any suggestions!
It is good by 'GQCNN-4.0-PJ' and always can grasp successfully. But it can't predict successfully by 'GQCNN-4.0-SUCTION'.
Our test image
the depth distance is 0.693m with Q=0.185
there have a point cloud file: https://drive.google.com/file/d/13iyM7MnbWEN_LE1hMO_S_Cwu3fr_XLZC/view?usp=sharing
The original image [ depth_0.npy ]
When grasp_candidates is opened
sampled grasps iter 0
sampled grasps iter 1
sampled grasps iter 2
Question
The original image's surface is smooth. I think maybe it is the cause that suction method can't be successful. Maybe I miss something, but now i don't know what happen clearly...
Think for any suggestions!