fuse_elevation — DRIVE `walkterrain` op

• Data kinds: images → depth

• Call: import fullseye as fs; fs.ledger.fuse_elevation(grids, agg: 'str' = 'max') (to call the implementation directly, import terrain; terrain.fuse_elevation(grids, agg: 'str' = 'max'); from the registry, opsdrive.get("fuse_elevation"))

• GPU: none (CPU reference implementation only)

Usage

Fuse several aligned elevation grids into one robot-centric map.

Multi-frame accumulation: as a robot walks it sees the terrain from several depth frames; binning each into an elevation_map on a common grid and fusing them here fills gaps and firms up heights. agg = 'max' (obstacle-safe, default), 'min' (ground-safe) or 'mean'. nan (unobserved in a given frame) is ignored; a cell unobserved in *every* frame stays nan. Input grids must share a shape.

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

• The canonical algorithm (author, year) and its uses are named in the family usage guide above.

Runnable examples (verified samples that actually call this op)

• walking_ops_tour — py -3.11 examples/walking_ops_tour.py

Ops the type connects to (they accept `depth` as input)

spin_from_marker_sequence · carla_transform_matrix · carla_pose_to_world · carla_camera_pose · carla_xy_yaw · carla_scene_load · town_chain · osm_parse

Same category (`walkterrain`)

elevation_map · fill_gaps · elevation_traversability · foothold_score · ground_surface · ground_plane · detect_obstacles · roughness_map

*Provenance: terrain.py — DRIVE operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

fuse_elevation — DRIVE walkterrain op