agv op• Data kinds: table → table
• Call: import fullseye as fs; fs.ledger.adg_build(paths) (to call the implementation directly, import agvfleet; agvfleet.adg_build(paths); from the registry, opsdrive.get("adg_build"))
Action dependency graph (Hönig, Kiesel, Tinka, Durham, Ayanian 2019).
Each vehicle's action = "enter the k-th cell of its sequence of cells to visit". There are two kinds of dependency:
(1) the same vehicle's previous action, (2) another vehicle that uses the same cell earlier leaving that cell (in plan time order).
Returns a dict: cells (each vehicle's cell sequence), deps ((i, k) → set of (j, m) that must finish before it). If the plan contains a collision, raises ValueError (the direction of the dependency cannot be determined).
• 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.
• poc_agv_fleet — py -3.11 examples/poc_agv_fleet.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
agv)warehouse_grid · grid_distances · mapf_cbs · mapf_ecbs · mapf_joint_astar · mapf_prioritized · plan_conflicts · plan_cost
*Provenance: agvfleet.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.