rss op• Data kinds: none → scalar (an op determined by its arguments alone — it takes no image or data input)
• Call: import fullseye as fs; fs.ledger.rss_stopping_distance(v: 'float', rho: 'float', accel: 'float', brake: 'float', v_max: 'Optional[float]' = None, direction: 'float' = 1.0) -> 'float' (to call the implementation directly, import rsssafety; rsssafety.rss_stopping_distance(v: 'float', rho: 'float', accel: 'float', brake: 'float', v_max: 'Optional[float]' = None, direction: 'float' = 1.0) -> 'float'; from the registry, opsdrive.get("rss_stopping_distance"))
Signed position offset under ad-rss-lib's stated braking pattern (1 formula shared by the longitudinal and lateral directions).
Accelerates with accel during ρ (capped at v_max), and adds the stopping distance direction · v_ρ > 0 only when the speed v_ρ after ρ is heading toward the other vehicle (direction · v_ρ² / (2 brake)). If heading away, it is not added (the calculateLongitudinalDistanceOffsetAfterStatedBrakingPattern test in the lib's calculateLateralDistanceOffsetAfterStatedBrakingPattern / signbit).
• direction = direction toward the other vehicle (+1 or −1). Longitudinally +1 (direction of travel = +x). Laterally, the left vehicle is +1 and the right vehicle −1.
• v is a signed speed (positive on the direction side means heading toward the other vehicle). Longitudinally, call with v ≥ 0.
• accel is signed and pointed to the direction side (ValueError unless direction · accel ≥ 0). Longitudinally +a_accel_max; laterally, left +a_lat, right −a_lat.
• brake is a positive magnitude. It always acts "in the direction that brings the speed toward the other vehicle to 0" (= the −direction side).
• v_max is the upper limit of the reached speed on the direction side (None = no limit). If |v| is already at or above it, no acceleration occurs.
Longitudinally (v ≥ 0, accel ≥ 0) this becomes v ρ + ½ a ρ² + (v + a ρ)²/(2 b), matching the travel distance of the following vehicle in Lemma 2 of the paper.
• 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_longitudinal — py -3.11 examples/poc_driving_longitudinal.py
scalar 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
rss)rss_params · rss_longitudinal_same · rss_longitudinal_opposite · rss_lateral · rss_longitudinal_check · rss_lateral_check · rss_worst_case_gap · rss_worst_case_gap_opposite
*Provenance: rsssafety.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.