search

graspnet / graspnet-baseline

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
https://graspnet.net/
Other
415 stars 133 forks source link

Camera positions with respect to robot reference frames #116

Closed davidea97 closed 5 days ago

davidea97 commented 6 days ago

Thanks for the great work! Is there any file reporting the camera extrinsic parameters which describe the relative position between the camera and a robot reference frame (e.g., the hand-eye transformation)?

chenxi-wang commented 5 days ago

Hi, the input point clouds and output grasps are in camera frame, so extrinsic parameters are not required during inference. In real robot experiments, you can transform the grasps according to your calibration result.