Robotic Grasping Pose Classification Dataset with Point Cloud Scores

Point cloud files for 47 common objects, with scores calculated for each point based on the PointNetGPD method. The dataset includes positive sample grasping poses after coordinate alignment. It was created by Wenlong Ji for the paper 'An efficient pose classification method for robotic grasping'.

Use Cases

• Training pose classification models based on point cloud data.
• Evaluating robotic grasping algorithms using pre-scored point clouds.
• Benchmarking coordinate alignment methods for grasping poses.

Strengths

• Contains 47 single-view point cloud files of common objects.
• Includes pre-calculated scores for each point based on the PointNetGPD method.

Limitations

• Row count and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

paperswithcode

Collection Method

Likely generated from experiments described in the associated research paper.