world op• Data kinds: table → table
• Call: import fullseye as fs; fs.ledger.world_build(course, *, props=(), kerb_height: 'float' = 0.15, kerb_width: 'float' = 0.3, lines: 'bool' = True, ground_margin: 'float' = 8.0, ground_step: 'float' = 4.0, joint_step: 'float' = 0.5, asset_root=None) -> 'dict' (to call the implementation directly, import driveworld; driveworld.world_build(course, *, props=(), kerb_height: 'float' = 0.15, kerb_width: 'float' = 0.3, lines: 'bool' = True, ground_margin: 'float' = 8.0, ground_step: 'float' = 4.0, joint_step: 'float' = 0.5, asset_root=None) -> 'dict'; from the registry, opsdrive.get("world_build"))
Builds a world from a course (element or layout).
Road surface = a plane covering everything (z = 0, label 0). Kerbs along the polygon edges of each element (label 1, excluding seam edges), and white lines 0.15 m inside the edges (label 9). Slopes are sloped meshes (label 0). Traffic signals are erected at the intersection's signal_poses (initial state "red", Japanese style: a pole on the far side + an arm carrying a horizontal 3-lamp head over the lane, roadjp), stop lines at stop_lines, and zebra stripes at crosswalks. props is a sequence of (asset_name, x, y, yaw) or (asset_name, x, y, yaw[, dims[, paint]]) (paint = car body colour, CAR_PAINTS). Returns {"V","F","face_label","face_color","objects","bounds","course"}.
Empty input (course an empty dict) raises ValueError.
• 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.
• gallery_drive_japan_roads — py -3.11 examples/gallery_drive_japan_roads.py
• gallery_drive_world_objects — py -3.11 examples/gallery_drive_world_objects.py
• poc_driving_longitudinal — py -3.11 examples/poc_driving_longitudinal.py
• poc_driving_school — py -3.11 examples/poc_driving_school.py
• poc_driving_weather — py -3.11 examples/poc_driving_weather.py
• poc_ttc_rss — py -3.11 examples/poc_ttc_rss.py
• poc_world_terrain — py -3.11 examples/poc_world_terrain.py
table as input)course_layout · course_occupancy · course_contains · world_camera · world_move · lidar_scan · rss_longitudinal_same · rss_longitudinal_opposite
world)world_camera · load_asset · world_move
*Provenance: driveworld.py — DRIVE operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.