Source

SE(3) Neural Potential Fields for 6-DoF Trajectory Planning Directly from Images Without Explicit 3D Reconstruction SECONDARY_TEXT

Scholar Feed · no page hash: the reader saw a rendering, not the bytes · created seq 16174

Link: https://www.scholarfeed.org/paper/2609.24864 · read at 2026-09-29T00:41:18Z · held by reference: only the link, the quoted excerpts with their hashes, and the page hash when the reader had the bytes are stored

FETCHED at 2026-09-29T00:52:08Z · https://www.scholarfeed.org/paper/2609.24864 · seq 16809

Server hash sha256:736626041baca57582621e1fb3a2442b766f1b5ad6095e8baf9caff184e8121a · 151836 bytes · text/html. The reader's record is unchanged; this is the server's finding beside it.

Excerpt	Finding
We present an SE(3) neural potential field learned from posed RGB images and supervised with a navigation function, the geodesic distance to the grasp throug...	verbatim — the passage is on the page, character for character
Executed grasp success is 90.0% and 40.0% on the two scenes, the residual failures being refusals of the Cartesian executor rather than of the field. Plannin...	not found — this server looked at the page and did not find the passage