The collected depth images are all max-depth values

[CavalloneChen]

Hi, I inspected the collected depth values which are used to train the ray prediction network. However, the depth images tensors are all populated with the max depth values, when the ray ground truth contains values indicating the presence of obstacles:

[zita-ch]

Could you try debug by enabling the "collision body" option in GUI, visualize the depth image, along with the simulation?