sunhan1997 / IndusGrasp

This is the official implementation of our paper: "A Novel Robotic Grasp Detection Framework Using Low-Cost RGB-D Camera for Industrial Bin Picking."
22 stars 2 forks source link

Some Questions #4

Open kkk7-byte opened 4 months ago

kkk7-byte commented 4 months ago

I cannot understand how to ensure that the grasping point is close to or located at the center of the object. For example, for parts such as bolts, the grasp path heatmap in the schematic diagram cannot show obvious local maximum values, which may be located at the edge of the path or other position.If the grasping point is located at the edge of the object, it may lead to unstable grasping.

sunhan1997 commented 4 months ago

In fact, with the grasping path, we cannot ensure that the grasp point is located at the object's center. But most of the time the grasp point is close to the object's center. Observing the obvious local maximum values in the schematic diagram is difficult because the difference between these values is very small. Of course, the grasp point may be located at the edge of the path, but in the grasping experiment, it does not lead to a significantly unstable grasp.

sunhan1997 commented 4 months ago

In fact, with the grasping path, we cannot ensure that the grasp point is located at the object's center. But most of the time the grasp point is close to the object's center. Observing the obvious local maximum values in the schematic diagram is difficult because the difference between these values is very small. Of course, the grasp point may be located at the edge of the path, but in the grasping experiment, it does not lead to a significantly unstable grasp.

孙晗

@. | ---- Replied Message ---- | From | @.> | | Date | 7/17/2024 14:38 | | To | @.> | | Cc | @.> | | Subject | [sunhan1997/IndusGrasp] Some Questions (Issue #4) |

I cannot understand how to ensure that the grasping point is close to or located at the center of the object. For example, for parts such as bolts, the grasp path heatmap in the schematic diagram cannot show obvious local maximum values, which may be located at the edge of the path or other position.If the grasping point is located at the edge of the object, it may lead to unstable grasping.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>

kkk7-byte commented 4 months ago

In fact, with the grasping path, we cannot ensure that the grasp point is located at the object's center. But most of the time the grasp point is close to the object's center. Observing the obvious local maximum values in the schematic diagram is difficult because the difference between these values is very small. Of course, the grasp point may be located at the edge of the path, but in the grasping experiment, it does not lead to a significantly unstable grasp.

Can you explain why most of the time the grasping point is close to the center of the object?Is it setting different values for different positions of the grasping path during annotation?