decide op• Data kinds: table → table
• Call: import fullseye as fs; fs.ledger.predict_amber_onset(observations, *, flash_duration: 'Optional[float]' = None, crossing_length: 'Optional[float]' = None, walk_speed: 'float' = 1.0, ped_red_to_amber: 'float' = 2.0, t_now: 'Optional[float]' = None) -> 'Dict[str, object]' (to call the implementation directly, import drivedecide; drivedecide.predict_amber_onset(observations, *, flash_duration: 'Optional[float]' = None, crossing_length: 'Optional[float]' = None, walk_speed: 'float' = 1.0, ped_red_to_amber: 'float' = 2.0, t_now: 'Optional[float]' = None) -> 'Dict[str, object]'; from the registry, opsdrive.get("predict_amber_onset"))
Estimates the start of the vehicle amber from observations of the parallel pedestrian signal ((t, state) in time order, state ∈ green / flash / red).
F = flash_duration (if absent, crossing_length / walk_speed), Δ = ped_red_to_amber. For each observed transition (green→flash, flash→red), an interval containing the amber time is formed, and their intersection is taken:
green→flash (last green t_g, first flash t_f): amber ∈ [t_g + F + Δ, t_f + F + Δ]
flash→red (last flash t_f', first red t_r): amber ∈ [t_f' + Δ, t_r + Δ]
Return value: amber_onset (midpoint of the interval), lo / hi, half_width (upper bound of the error), remaining = amber_onset − t_now (default = time of the last observation), basis (the transitions used). If there is not a single transition, ValueError (green merely continuing does not tell "when it will start flashing"). An empty interval (observations contradict F and Δ) is also 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.
• poc_driving_decisions — py -3.11 examples/poc_driving_decisions.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
decide)mirror_reflection_matrix · mirror_virtual_camera · mirror_aim_normal · convex_mirror_fov · mirror_blind_zone · check_sequence_score · signal_phase_plan · signal_state
*Provenance: drivedecide.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.