This post has NOT been accepted by the mailing list yet.
I am trying to take a model of a primitive shape like a cylinder and find a place in a point cloud that the shape would fit. If you think of a model of a peg and the environment is a peg board. I am trying to find places where the peg would fit. I have been trying to adapt the segmentation methods, but it seems many are looking for a cluster of points and I am looking for the negative space. Has anyone had any luck with something like this or have any ideas on how to solve it? I am currently exploring using normals to try and fit the inverted normals of the model to the environment, but I don't know if there is a better way to do this. Any help is greatly appreciated.