roverslip op• Data kinds: signal × signal → table
• Call: import fullseye as fs; fs.ledger.slip_gp_fit(slopes, slips, length_scales=None, noise_levels=None) -> 'dict' (to call the implementation directly, import roverslip; roverslip.slip_gp_fit(slopes, slips, length_scales=None, noise_levels=None) -> 'dict'; from the registry, opsdrive.get("slip_gp_fit"))
Gaussian process from slope angle to slip ratio (RBF kernel + homoscedastic observation noise). Hyperparameters by grid search on the log marginal likelihood.
y is fitted after subtracting the mean and dividing by the standard deviation (signal variance fixed at σ_f² = 1; searches over ℓ and noise σ_n). The default length_scales is 16 steps (log-spaced) from 0.05 to 2 times the angle range, and noise_levels is 16 steps from 0.01 to 1 (in units of normalised y). The return value is a dict used for prediction (kind = "gp", x, alpha, L, ell, noise, y_mean, y_scale, log_marginal_likelihood). For data whose noise varies with angle (heteroscedastic), the band has the width of the overall average (a trap for the gate).
• 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_soil_tactile — py -3.11 examples/gallery_drive_soil_tactile.py
• poc_rover_slip_risk_path — py -3.11 examples/poc_rover_slip_risk_path.py
table as input)course_layout · course_occupancy · course_contains · world_build · world_camera · world_move · lidar_scan · rss_longitudinal_same
roverslip)bekker_pressure · bekker_wheel_sinkage · wheel_forces · wheel_sinkage · wheel_traction_curve · slope_slip_curve · ground_shift_track · odometry_slip
*Provenance: roverslip.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.