Sheng Zhong (Johnson)

Strangely, if I treat the mesh as a legacy mesh then it will let me construct it with the RaycastingScene(): ```python mesh = o3d.t.geometry.TriangleMesh.from_legacy(mesh) # # mesh.compute_vertex_normals() scene = o3d.t.geometry.RaycastingScene()...

Using the `check_properties` function from http://www.open3d.org/docs/latest/tutorial/geometry/mesh.html I see a lot of spurious boundaries (green lines) and non-manifold vertices (blue points), but none of the reported intersecting triangles (pink lines). 

My current primary goal is to incorporate freespace information more so than surface normal information. Results are currently quite good; I'm currently comparing against more freespace-aware baselines and also trying...

Hey guys, I just published an RSS paper on this problem: [https://www.roboticsproceedings.org/rss19/p077.pdf](https://www.roboticsproceedings.org/rss19/p077.pdf) and a standalone library package (experiments are in a separate package) published to pypi and is pip installable...

Hi, for simplicity and consistency all the coordinates are given in robot frame. For a floating-base robot inside of a global world frame, you'll need to manage the world-to-robot and...

Any luck with this?

Yeah, not sure what would be a good solution for monitoring in this case. For example, between execution steps (pokes), the trend of the norm QD score with more optimization...

I see, thanks will check that out! It's theoretically unbounded, but I think empirically I can set a bound. In this case unexplored bins will receive the score offset instead...

Tried this out and it seems to work fine: concerning that my CMAMEGA is doing worse than CMAME though - thoughts? 

> Without more information about the domain its hard to tell if the issue is setup for the DQD algorithm or a domain where derivative-free QD works better than DQD....