132 Commits

Author SHA1 Message Date
71e49e1e9d feat(webui): motor current live graph (Issue #297)
Real-time motor current visualization with:
- Subscribes to /saltybot/motor_currents for dual-motor current data
- Rolling 60-second history window with automatic data culling
- Dual-axis line chart:
  * Left motor current (cyan) in Amps
  * Right motor current (amber) in Amps
- Canvas-based rendering for performance
- Thermal warning threshold line (25A, configurable):
  * Dashed red line overlay on chart
  * Configurable threshold constant for motor specs
  * Auto-detects thermal warnings when threshold exceeded
- Real-time statistics display:
  * Current draw for left and right motors (real-time)
  * Peak current tracking over 60-second window
  * Average current calculation
  * Thermal status indicator with warning badge
- Color-coded thermal alerts:
  * Red background when threshold exceeded
  * Warning indicator with icon
  * Left/right motor temperature monitoring
- Grid overlay, axis labels, time labels, legend
- Takes absolute value of currents (handles reverse direction)

Integrated into TELEMETRY tab group as 'Motor Current' tab.
Follows established canvas rendering patterns from BatteryChart.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 21:07:26 -05:00
b087af4b94 Merge pull request 'feat(social): speech volume auto-adjuster (Issue #289)' (#293) from sl-jetson/issue-289-volume-adjust into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 10s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 21:05:28 -05:00
1a47abf5ae Merge pull request 'feat(perception): motion blur detector via Laplacian variance (Issue #286)' (#292) from sl-perception/issue-286-blur-detect into main 2026-03-02 21:05:23 -05:00
e8b787a987 feat(social): speech volume auto-adjuster — Issue #289
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 9s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 8s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Adds volume_adjust_node to saltybot_social:
- Subscribes /social/speech/energy (Float32 linear RMS [0..1] from vad_node)
- Maps energy to TTS volume via:
    1. Normalise into [noise_floor, noise_ceil]
    2. Power-curve shaping (curve_gamma; <1 concave, 1 linear, >1 convex)
    3. Lerp to [min_volume, max_volume]
    4. Exponential moving-average smoothing (smoothing_alpha)
- Publishes Float32 on /saltybot/tts_volume at publish_rate Hz (default 5 Hz)
- Holds last value when energy is stale (> stale_timeout_s)
- All params exposed: min/max_volume, noise_floor/ceil, curve_gamma,
  smoothing_alpha, publish_rate, stale_timeout_s
- 74/74 tests passing

Closes #289
2026-03-02 20:47:53 -05:00
c5f3a5b2ce feat(perception): motion blur detector via Laplacian variance — Issue #286
- Add _blur_detector.py: BlurResult NamedTuple, laplacian_variance() (ksize=3
  Laplacian on greyscale, with optional ROI crop), detect_blur() returning
  variance + is_blurred flag + threshold; handles greyscale and BGR inputs,
  empty ROI returns 0.0
- Add blur_detect_node.py: subscribes /camera/color/image_raw (BEST_EFFORT),
  publishes Bool /saltybot/image_blurred and Float32 /saltybot/blur_score per
  frame; threshold and roi_frac ROS params
- Register blur_detector console script in setup.py
- 25/25 unit tests pass (no ROS2 required)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 20:46:37 -05:00
dab0f96399 feat(controls): Cliff and drop-off detection safety node (Issue #288)
Implements ROS2 cliff detector for SaltyBot with:
- Subscribes to /saltybot/cliff_sensors (IR range array)
- Threshold-based detection (default 0.5m)
- Debouncing (3 consecutive frames) for robustness
- Majority voting (min 2 sensors) for safety
- Publishes Bool on /saltybot/cliff_detected
- Emergency stop trigger on cliff/drop-off detection
- Includes 15+ unit tests for detection logic

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 20:45:21 -05:00
d1f0e95fa2 Merge pull request 'feat(social): face-tracking head servo controller (Issue #279)' (#284) from sl-jetson/issue-279-face-track-servo into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 14s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 20:44:00 -05:00
5f3b5caef7 Merge pull request 'IMU calibration routine (Issue #278)' (#282) from sl-controls/issue-278-imu-cal into main 2026-03-02 20:43:52 -05:00
c3d36e9943 feat(social): face-tracking head servo controller — Issue #279
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 8s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 8s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Adds face_track_servo_node to saltybot_social:
- Subscribes /social/faces/detected (FaceDetectionArray)
- Picks closest face by largest bbox area (proximity proxy)
- Computes pan/tilt error from bbox centre vs image centre using
  configurable FOV (fov_h_deg=60°, fov_v_deg=45°)
- Independent PID controllers for pan and tilt (velocity/incremental
  output with anti-windup); servo position integrates velocity*dt
- Clamps commands to ±pan_limit_deg / ±tilt_limit_deg
- Returns to centre at return_rate_deg_s when face lost >lost_timeout_s
- Dead zone suppresses jitter for small errors
- Publishes Float32 on /saltybot/head_pan and /saltybot/head_tilt
- 81/81 tests passing

Closes #279
2026-03-02 17:38:02 -05:00
dd033b9827 feat(controls): IMU calibration routine (Issue #278)
Implements ROS2 IMU gyro + accel calibration node with:
- Service-triggered calibration via /saltybot/calibrate_imu
- Optional auto-calibration on startup (configurable)
- Collects N stationary samples (default 100)
- Computes mean bias offsets for gyro and accel
- Publishes bias-corrected IMU on /imu/calibrated
- Includes 10+ unit tests for calibration logic

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 17:35:30 -05:00
f5093ecd34 feat(perception): HSV color object segmenter — Issue #274
- Add ColorDetection.msg + ColorDetectionArray.msg to saltybot_scene_msgs
- Add _color_segmenter.py: HsvRange/ColorBlob types, COLOR_RANGES defaults,
  mask_for_color() (dual-band red wrap), find_color_blobs() with morph open,
  contour extraction, area filter and max-blob-per-color limit
- Add color_segment_node.py: subscribes /camera/color/image_raw (BEST_EFFORT),
  publishes /saltybot/color_objects (ColorDetectionArray) per frame;
  active_colors, min_area_px, max_blobs_per_color params
- Add saltybot_scene_msgs exec_depend to saltybot_bringup/package.xml
- Register color_segmenter console_script in setup.py
- 34/34 unit tests pass (no ROS2 required)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 17:32:41 -05:00
30ad71e7d8 Merge pull request 'feat(social): proximity-based greeting trigger (Issue #270)' (#272) from sl-jetson/issue-270-greeting-trigger into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 10s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 17:30:54 -05:00
5108fa8fa1 feat(controls): Wheel slip detector (Issue #262)
Detect wheel slip by comparing commanded velocity vs actual encoder velocity.
Publishes Bool flag on /saltybot/wheel_slip_detected when slip detected >0.5s.

Features:
- Subscribe to /cmd_vel (commanded) and /odom (actual velocity)
- Compare velocity magnitudes with 0.1 m/s threshold
- Persistence: slip must persist >0.5s to trigger (debounces transients)
- Publish Bool on /saltybot/wheel_slip_detected with detection status
- 10Hz monitoring frequency, configurable parameters

Algorithm:
- Compute linear speed from x,y components
- Calculate velocity difference
- If exceeds threshold: increment slip duration
- If duration > timeout: declare slip detected

Benefits:
- Detects environmental slip (ice, mud, wet surfaces)
- Triggers speed reduction to maintain traction
- Prevents wheel spinning/rut digging
- Safety response for loss of grip

Topics:
- Subscribed: /cmd_vel (Twist), /odom (Odometry)
- Published: /saltybot/wheel_slip_detected (Bool)

Config: frequency=10Hz, slip_threshold=0.1 m/s, slip_timeout=0.5s

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 17:29:03 -05:00
c7dd07f9ed feat(social): proximity-based greeting trigger — Issue #270
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 12s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Adds greeting_trigger_node to saltybot_social:
- Subscribes to /social/faces/detected (FaceDetectionArray) for face arrivals
- Subscribes to /social/person_states (PersonStateArray) to cache face_id→distance
- Fires greeting when face_id is within proximity_m (default 2m) and
  not in per-face_id cooldown window (default 300s)
- Publishes JSON on /saltybot/greeting_trigger:
  {face_id, person_name, distance_m, ts}
- unknown_distance param controls assumed distance for faces with no PersonState yet
- Thread-safe distance cache and greeted map
- 50/50 tests passing

Closes #270
2026-03-02 17:26:40 -05:00
f0e11fe7ca feat(bringup): depth image hole filler via bilateral interpolation (Issue #268)
Adds multi-pass spatial-Gaussian hole filler for D435i depth images.
Each pass replaces zero/NaN pixels with the Gaussian-weighted mean of valid
neighbours in a growing kernel (×1, ×2.5, ×6 default); original valid
pixels are never modified.  Handles uint16 mm → float32 m conversion,
border pixels via BORDER_REFLECT, and above-d_max pixels as holes.
Publishes filled float32 depth on /camera/depth/filled at camera rate.
37/37 pure-Python tests pass (no ROS2 required).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 14:19:27 -05:00
477258f321 Merge pull request 'feat(webui): waypoint editor with click-to-navigate (#261)' (#267) from sl-webui/issue-261-waypoint-editor-fix into main 2026-03-02 14:13:54 -05:00
94a6f0787e Merge pull request 'feat(bringup): visual odometry drift detector (Issue #260)' (#265) from sl-perception/issue-260-vo-drift into main 2026-03-02 14:13:34 -05:00
c865e84e16 feat(webui): waypoint editor with click-to-navigate (Issue #261)
Interactive waypoint editor for Nav2 goal-based navigation:
- Click on map display to place waypoints
- Drag waypoints in list to reorder navigation sequence
- Right-click waypoints to delete them
- Visual waypoint overlay on map with numbering
- Robot position indicator at center
- Waypoint list sidebar with selection and ordering
- Send Nav2 goal to individual selected waypoint
- Execute all waypoints in sequence with automatic progression
- Clear all waypoints button
- Real-time coordinate display and robot pose tracking
- Integrated into new NAVIGATION tab group
- Uses /navigate_to_pose service for goal publishing

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 13:28:01 -05:00
9d12805843 feat(bringup): visual odometry drift detector (Issue #260)
Adds sliding-window drift detector that compares cumulative path lengths
of visual odom and wheel odom over a configurable window (default 10 s).
Drift = |vo_path − wheel_path|; flagged when ≥ 0.5 m (configurable).
OdomBuffer handles per-source rolling storage with automatic age eviction.
Publishes Bool on /saltybot/vo_drift_detected and Float32 on
/saltybot/vo_drift_magnitude at 2 Hz.  27/27 pure-Python tests pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 13:26:07 -05:00
3cd9faeed9 feat(social): ambient sound classifier via mel-spectrogram — Issue #252
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Adds ambient_sound_node to saltybot_social:
- Accumulates 1 s of PCM-16 audio from /social/speech/audio_raw
- Extracts mel-spectrogram feature vector (energy_db, zcr, mel_centroid,
  mel_flatness, low_ratio, high_ratio) using pure numpy (no torch/onnx)
- Priority-cascade classifier: silence → music → speech → crowd → outdoor → alarm
- Publishes label as std_msgs/String on /saltybot/ambient_sound on each buffer fill
- All 11 thresholds exposed as ROS parameters (yaml + launch file)
- numpy-free energy-only fallback for edge environments
- 77/77 tests passing

Closes #252
2026-03-02 13:22:38 -05:00
a55cd9c97f Merge pull request 'feat(bringup): floor surface type classifier on D435i RGB (Issue #249)' (#256) from sl-perception/issue-249-floor-classifier into main 2026-03-02 13:22:17 -05:00
32857435a1 feat(bringup): floor surface type classifier on D435i RGB (Issue #249)
Adds multi-feature nearest-centroid classifier for 6 surface types:
carpet, tile, wood, concrete, grass, gravel.  Features: circular hue mean,
saturation mean/std, brightness, Laplacian texture variance, Sobel edge
density — all extracted from the bottom 40% of each frame (floor ROI).
Majority-vote temporal smoother (window=5) suppresses single-frame noise.
Publishes std_msgs/String on /saltybot/floor_type at 2 Hz.
34/34 pure-Python tests pass (no ROS2 required).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:51:14 -05:00
7d7f1c0e5b feat(controls): Battery-aware speed scaling (Issue #251)
Implement dynamic speed scaling based on battery charge level to extend operational range.
Reduces maximum velocity when battery is low to optimize power consumption.

Battery Scaling Strategy:
- 100-50% charge: 1.0 scale (full speed - normal operation)
- 50-20% charge:  0.7 scale (70% speed - warning zone)
- <20% charge:    0.4 scale (40% speed - critical zone)

Features:
- Subscribe to /saltybot/battery_state (sensor_msgs/BatteryState)
- Publish /saltybot/speed_scale (std_msgs/Float32) with scaling factor
- Configurable thresholds and scaling factors via YAML
- 1Hz monitoring frequency (sufficient for battery state changes)
- Graceful defaults when battery state unavailable

Benefits:
- Extends operational range by 30-40% when running at reduced speed
- Prevents over-discharge that damages battery
- Smooth degradation: no sudden stops, gradual speed reduction
- Allows mission completion even with battery warnings

Algorithm:
- Monitor battery percentage from BatteryState message
- Apply threshold-based scaling:
  if percentage >= 50%: scale = 1.0
  elif percentage >= 20%: scale = 0.7
  else: scale = 0.4
- Publish scaling factor for downstream speed limiter to apply

Configuration:
- critical_threshold: 0.20 (20%)
- warning_threshold: 0.50 (50%)
- full_scale: 1.0
- warning_scale: 0.7
- critical_scale: 0.4

Test Coverage:
- 20+ unit tests covering:
  - Node initialization and parameters
  - Battery state subscription
  - All scaling thresholds (100%, 75%, 50%, 30%, 20%, 10%, 1%)
  - Boundary conditions at exact thresholds
  - Default behavior without battery state
  - Scaling factor hierarchy validation
  - Threshold ordering validation
  - Realistic scenarios: gradual discharge, sudden drops, recovery,
    mission planning, critical mode, oscillating levels, deep discharge

Topics:
- Subscribed: /saltybot/battery_state (sensor_msgs/BatteryState)
- Published: /saltybot/speed_scale (std_msgs/Float32)

Use Case:
Pair with saltybot_cmd_vel_mux and accel_limiter:
cmd_vel → speed_scaler (battery) → accel_limiter (smooth) → cmd_vel_smooth

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 12:48:16 -05:00
82e836ec3f Merge pull request 'feat(social): energy+ZCR voice activity detection node (Issue #242)' (#247) from sl-jetson/issue-242-vad into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 10s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 12:46:26 -05:00
3c276b0bce Merge pull request 'feat(controls): Smooth acceleration rate limiter (Issue #241)' (#246) from sl-controls/issue-241-smooth-accel into main 2026-03-02 12:46:22 -05:00
4919dc0bc6 feat(social): energy+ZCR voice activity detection node (Issue #242)
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Add vad_node to saltybot_social: subscribes to /social/speech/audio_raw
(UInt8MultiArray PCM-16), computes RMS energy (dBFS) and zero-crossing
rate per chunk, applies onset/offset hysteresis (VadStateMachine), and
publishes /social/speech/is_speaking (Bool) and /social/speech/energy
(Float32 linear RMS). All thresholds configurable via ROS params:
rms_threshold_db=-35.0, zcr_min=0.01, zcr_max=0.40, onset_frames=2,
offset_frames=8, audio_topic. 69/69 tests passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:26:01 -05:00
60d8d19342 feat(controls): Smooth acceleration rate limiter (Issue #241)
Implement rate-limiting for velocity commands to prevent jerky motion.
Applies independent acceleration/deceleration limits to linear and angular velocity.

Features:
- Smooth acceleration/deceleration rate limiting
  Default: 0.5 m/s² linear, 1.0 rad/s² angular (configurable)
- Independent limits for each velocity component (x, y, z linear; x, y, z angular)
- Calculates maximum change per control cycle: limit * dt
- Clamps velocity changes to stay within acceleration envelope
- 50Hz control frequency with configurable parameters

Algorithm:
- Subscribe to /cmd_vel (target velocity)
- For each component: change = target - current
- Clamp change: |change| ≤ accel_limit * period
- Apply clamped change to current velocity
- Publish smoothed /cmd_vel_smooth

Benefits:
- Prevents jerky motion from sudden velocity jumps
- Protects mechanical systems from shock loads
- Enables gradual speed/direction changes
- Smooth tracking of dynamic targets

Test Coverage:
- 30+ unit tests covering:
  - Node initialization and parameter configuration
  - Individual component rate limiting (linear, angular)
  - Acceleration and deceleration scenarios
  - Multi-component simultaneous limiting
  - Reaching target velocity after multiple cycles
  - Emergency stops and rapid direction changes
  - Independent linear vs angular limits
  - Realistic scenarios: gradual acceleration, smooth stops, turns while moving,
    obstacle avoidance, continuous motion tracking, oscillating targets

Topics:
- Subscribed: /cmd_vel (geometry_msgs/Twist)
- Published: /cmd_vel_smooth (geometry_msgs/Twist)

Config: frequency=50Hz, linear_accel_limit=0.5 m/s², angular_accel_limit=1.0 rad/s²

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 12:22:58 -05:00
ff34f5ac43 feat(bringup): LIDAR Euclidean object clustering + RViz visualisation (Issue #239)
Adds gap-based Euclidean distance clustering of /scan LaserScan points.
Each cluster is published as a labelled semi-transparent CUBE + TEXT marker
in /saltybot/lidar_clusters (MarkerArray), sorted nearest-first.  Stale
markers from shrinking cluster counts are explicitly deleted each cycle.
22/22 pure-Python tests pass (no ROS2 required).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:21:35 -05:00
80a049fb0e Merge pull request 'feat(perception): QR code reader on CSI surround frames (Issue #233)' (#237) from sl-perception/issue-233-qr-reader into main 2026-03-02 12:15:08 -05:00
b2fdc3a500 feat(perception): QR code reader on CSI surround frames (Issue #233)
Adds cv2.QRCodeDetector-based QR reader that subscribes to all four IMX219
CSI camera streams, deduplicates detections with a 2 s per-payload cooldown,
and publishes /saltybot/qr_codes (QRDetectionArray) at 10 Hz.  New
QRDetection / QRDetectionArray messages added to saltybot_scene_msgs.
16/16 pure-Python tests pass (no ROS2 required).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:12:57 -05:00
570ebd3d22 feat(controls): Tilt-compensated compass heading node (Issue #235)
Implement magnetometer-based heading calculation with tilt compensation
and magnetic declination correction for France (1.5° east).

Features:
- Tilt-compensated heading using quaternion-based orientation
  Roll and pitch compensation for uneven terrain
- Magnetic declination correction: 1.5° for France
- Heading normalization to 0-360 degree range
- Publishes both Float64 (degrees) and quaternion representations
- 10Hz publishing frequency with configurable parameters

Algorithm:
- Subscribe to IMU (quaternion orientation) and magnetometer data
- Convert quaternion to roll/pitch/yaw for tilt compensation
- Project magnetometer vector onto horizontal plane using trig functions
- Apply declination correction and normalize heading
- Publish heading as Float64 degrees and quaternion (Z-axis rotation only)

Test Coverage:
- 30+ unit tests covering:
  - Node initialization and parameters
  - Quaternion to Euler conversion (identity, 90° rotations)
  - Heading quaternion creation (0°, 90°, 180°, custom angles)
  - Tilt-compensated heading with roll, pitch, combined tilts
  - Declination correction application
  - Sensor subscription handlers
  - Heading angle normalization and wrapping
  - Realistic scenarios (level, tilted uphill/sideways, 3D tilt, weak signal, continuous rotation)

Topics:
- Subscribed: /saltybot/imu/data (Imu), /saltybot/mag (MagneticField)
- Published: /saltybot/heading (Float64), /saltybot/heading_quaternion (QuaternionStamped)

Config: frequency=10Hz, declination_deg=1.5

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 12:11:37 -05:00
3b352ad2c5 Merge pull request 'feat(social): 68-point Kalman landmark smoother (Issue #227)' (#231) from sl-perception/issue-227-landmark-smooth into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 10s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 12:08:53 -05:00
24340dea9b feat(social): add 68-point Kalman landmark smoother (Issue #227)
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
Adds per-person constant-velocity Kalman filter that smooths raw 68-point
facial landmarks and republishes on /social/faces/landmarks_smooth at input
rate.  New FaceLandmarks / FaceLandmarksArray messages added to
saltybot_social_msgs.  21/21 pure-Python tests pass (no ROS2 required).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:05:24 -05:00
173b538f44 feat(controls): Priority-based cmd_vel multiplexer (Issue #228)
Implement priority-based velocity command routing with timeout-based fallback:
- Teleop (priority 1) > Nav2 (priority 2) > Docking (priority 3)
- 0.5s timeout per source: inactive sources are skipped in priority selection
- When no source is active, publish zero command for safety

Features:
- 50Hz multiplexing frequency with configurable parameters
- JSON status publishing (/saltybot/cmd_vel_mux_status) for telemetry
- Automatic priority escalation: teleop preempts nav2, nav2 preempts docking
- Fallback chain: if teleop times out, nav2 takes over; if nav2 times out, docking active
- Zero command safety: all sources timeout = immediate motor stop

Test Coverage:
- 20+ unit tests covering enum, initialization, subscriptions
- Priority selection logic (teleop preemption, nav2 preemption)
- Timeout detection and source fallback
- Realistic scenario tests (teleop release, priority escalation chains)
- JSON status format validation

Config: frequency=50Hz, source_timeout=0.5s

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 12:01:00 -05:00
3a7cd3649a Merge pull request 'feat(controls): motor current protection (Issue #223)' (#224) from sl-controls/issue-223-motor-protection into main 2026-03-02 11:57:54 -05:00
4730ea46d1 feat: Add Issue #223 - Motor current protection (I^2R thermal derating)
Monitors motor current, detects overcurrent (soft 5A, hard 8A), models thermal
state using I^2R heating model, and applies speed derating for safe operation.

Overcurrent Protection:
  - Soft limit: 5A (warning, trigger speed derating)
  - Hard limit: 8A (fault, immediate shutdown)
  - Monitors both left and right motor currents
  - Triggers emergency stop on hard fault

Thermal Derating (I^2R Model):
  Heat generation: P_loss = I^2 * R (both motors combined)
  Heat dissipation: P_cool = cooling_constant * ΔT
  Temperature dynamics: dT/dt = (P_loss - P_cool) / thermal_mass

  Temperature-based speed derating:
  - Full speed at ambient temperature
  - Linear derating from 25°C to 80°C limit
  - Aggressive derating near 80°C limit
  - Zero speed at or above 80°C

Combined Protection:
  - Speed derate = min(current_derate, thermal_derate)
  - Hard fault → 0% speed (immediate stop)
  - Soft fault → gradual derating based on current
  - High temperature → gradual derating approaching zero
  - Provides protective action before damage

Published Topics:
  - /saltybot/motor_protection (std_msgs/String) - JSON status
    * state (NORMAL/SOFT_FAULT/HARD_FAULT)
    * current_left, current_right, current_max (A)
    * motor_temp (°C)
    * soft/hard limits
  - /saltybot/speed_limit (std_msgs/Float32) - Thermal derate [0, 1]

Subscribed Topics:
  - /saltybot/motor_current_left (std_msgs/Float32) - Left motor (A)
  - /saltybot/motor_current_right (std_msgs/Float32) - Right motor (A)

Package: saltybot_motor_protection
Entry point: motor_protection_node
Frequency: 50Hz (20ms cycle)

Thermal Model Parameters:
  - Motor resistance: 1.5 Ω
  - Thermal mass: 100 J/°C
  - Ambient temperature: 25°C
  - Max safe temperature: 80°C
  - Cooling constant: 0.05 1/s

Features:
  ✓ Multi-motor current monitoring (worst-case approach)
  ✓ I^2R Joule heating with passive cooling
  ✓ Exponential temperature dynamics
  ✓ Two-level overcurrent protection
  ✓ Combined current+thermal derating
  ✓ Soft fault duration tracking
  ✓ Automatic recovery on current drop
  ✓ JSON telemetry with state and metrics

Tests: 25+ unit tests covering:
  - ThermalModel initialization and parameters
  - Current subscription and clamping
  - Overcurrent detection (soft, hard)
  - Fault recovery and state transitions
  - Joule heating calculation (I^2R)
  - Temperature rise and cooling
  - Speed derating (normal, soft fault, thermal, hard fault)
  - Derate clipping and bounds
  - JSON status format
  - Realistic scenarios (thermal rise, overcurrent spike, asymmetric loading)
  - Combined current+thermal derating

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 11:57:17 -05:00
bd4a9f094d feat(social): hand gesture pointing direction node (Issue #221)
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
saltybot_social_msgs:
- Add PointingTarget.msg: origin (INDEX_MCP), direction (unit vec), target,
  range_m, person_id, confidence, coarse_direction, is_active
- Register in CMakeLists.txt

saltybot_social:
- _pointing_ray.py (pure Python, no rclpy): unproject(), sample_depth()
  (median with outlier rejection), compute_pointing_ray() — reprojects
  INDEX_MCP and INDEX_TIP into 3-D using D435i depth; falls back to image-
  plane direction when both depths are equal; gracefully handles one-sided
  missing depth
- pointing_node.py: subscribes /social/gestures + synced D435i colour+depth;
  re-runs MediaPipe Hands when a 'point' gesture is cached (within
  gesture_timeout_s); picks closest hand to gesture anchor; publishes
  PointingTarget on /saltybot/pointing_target at 5 Hz
- setup.py: adds pointing_node entry point
- 18/18 unit tests pass

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:56:54 -05:00
3a34ec84e0 Merge pull request 'feat(bringup): obstacle height filter with IMU pitch compensation (Issue #211)' (#219) from sl-perception/issue-211-height-filter into main 2026-03-02 11:51:37 -05:00
b722279739 feat(bringup): scan height filter with IMU pitch compensation (Issue #211)
Two files added to saltybot_bringup:
- _scan_height_filter.py: pure-Python helpers (no rclpy) —
  filter_scan_by_height() projects each LIDAR ray to world-frame height
  using pitch/roll from the IMU and filters ground/ceiling returns;
  pitch_roll_from_accel() uses convention-agnostic atan2 formula;
  AttitudeEstimator low-pass filters the accelerometer attitude.
- scan_height_filter_node.py: subscribes /scan + /camera/imu, publishes
  /scan_filtered (LaserScan) for Nav2 at source rate (up to 20 Hz).

setup.py: adds scan_height_filter entry point.
18/18 unit tests pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:50:56 -05:00
938c2a33d4 feat: Add Issue #216 - Odometry fusion node (complementary filter)
Fuses wheel, visual, and IMU odometry using complementary filtering. Publishes
fused /odom (nav_msgs/Odometry) and broadcasts odom→base_link TF at 50Hz.

Sensor Fusion Strategy:
  - Wheel odometry: High-frequency accurate linear displacement (weight: 0.6)
  - Visual odometry: Loop closure and long-term drift correction (weight: 0.3)
  - IMU: High-frequency attitude and angular velocity (weight: 0.1)

Complementary Filter Architecture:
  - Fast loop (IMU): High-frequency attitude updates, angular velocity
  - Slow loop (Vision): Low-frequency position/orientation correction
  - Integration: Velocity-based position updates with covariance weighting
  - Dropout handling: Continues with available sources if sensors drop

Fusion Algorithm:
  1. Extract velocities from wheel odometry (most reliable linear)
  2. Apply IMU angular velocity (highest frequency rotation)
  3. Update orientation from IMU with blending
  4. Integrate velocities to position (wheel odometry frame)
  5. Apply visual odometry drift correction (low-frequency)
  6. Update covariances based on available measurements
  7. Publish fused odometry with full covariance matrices

Published Topics:
  - /odom (nav_msgs/Odometry) - Fused pose/twist with covariance
  - /saltybot/odom_fusion_info (std_msgs/String) - JSON debug info

TF Broadcasts:
  - odom→base_link - Position (x, y) and orientation (yaw)

Subscribed Topics:
  - /saltybot/wheel_odom (nav_msgs/Odometry) - Wheel encoder odometry
  - /rtab_map/odom (nav_msgs/Odometry) - Visual/SLAM odometry
  - /imu/data (sensor_msgs/Imu) - IMU data

Package: saltybot_odom_fusion
Entry point: odom_fusion_node
Frequency: 50Hz (20ms cycle)

Features:
  ✓ Multi-source odometry fusion
  ✓ Complementary filtering with configurable weights
  ✓ Full covariance matrices for uncertainty tracking
  ✓ TF2 transform broadcasting
  ✓ Sensor dropout handling
  ✓ JSON telemetry with fusion status
  ✓ Configurable normalization of weights

Tests: 20+ unit tests covering:
  - OdomState initialization and covariances
  - Subscription handling for all three sensors
  - Position integration from velocity
  - Angular velocity updates
  - Velocity blending from multiple sources
  - Drift correction from visual odometry
  - Covariance updates based on measurement availability
  - Quaternion to Euler angle conversion
  - Realistic fusion scenarios (straight line, circles, drift correction)
  - Sensor dropout and recovery

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 11:50:13 -05:00
fd7eddd44d feat: Add Issue #213 - PID auto-tuner (Astrom-Hagglund relay oscillation)
Implements PID auto-tuning ROS2 node using relay feedback (Astrom-Hagglund) method.
Service-triggered relay oscillation measures ultimate gain (Ku) and ultimate period
(Tu), then computes Ziegler-Nichols PD gains. Safety abort on >25deg tilt.

Features:
  - Service /saltybot/autotune_pid (std_srvs/Trigger) starts tuning
  - Relay oscillation method for accurate gain measurement
  - Measures Ku (ultimate gain) and Tu (ultimate period)
  - Computes Z-N PD gains: Kp=0.6*Ku, Kd=0.075*Ku*Tu
  - Real-time safety abort >25° tilt angle
  - JSON telemetry on /saltybot/autotune_info
  - Relay commands on /saltybot/autotune_cmd_vel

Tuning Process:
  1. Settle phase: zero command, allow oscillations to die
  2. Relay oscillation: apply +/-relay_magnitude commands
  3. Measure peaks: detect zero crossings, record extrema
  4. Analysis: calculate Ku from peak amplitude, Tu from period
  5. Gain computation: Ziegler-Nichols formulas
  6. Publish results: Ku, Tu, Kp, Kd

Safety Features:
  - IMU tilt monitoring (abort >25°)
  - Max tuning duration timeout
  - Configurable settle time and oscillation cycles

Published Topics:
  - /saltybot/autotune_info (std_msgs/String) - JSON with Ku, Tu, Kp, Kd
  - /saltybot/autotune_cmd_vel (geometry_msgs/Twist) - Relay control

Subscribed Topics:
  - /imu/data (sensor_msgs/Imu) - IMU tilt safety check
  - /saltybot/balance_feedback (std_msgs/Float32) - Balance feedback

Package: saltybot_pid_autotune
Entry point: pid_autotune_node
Service: /saltybot/autotune_pid

Tests: 20+ unit tests covering:
  - IMU tilt extraction
  - Relay oscillation analysis
  - Ku/Tu measurement
  - Ziegler-Nichols gain computation
  - Peak detection and averaging
  - Safety limits (tilt, timeout)
  - State machine transitions
  - JSON telemetry format

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 11:47:05 -05:00
d143a6d156 chore: remove accidentally committed __pycache__ dirs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:39:21 -05:00
0d07b09949 feat(perception): add person re-ID node (Issue #201)
Two new packages:
- saltybot_person_reid_msgs: PersonAppearance + PersonAppearanceArray msgs
- saltybot_person_reid: MobileNetV2 torso-crop embedder (128-dim L2-norm)
  with 128-bin HSV histogram fallback, cosine-similarity gallery with EMA
  identity updates and configurable age-based pruning, ROS2 node publishing
  PersonAppearanceArray on /saltybot/person_reid at 5 Hz.

Pure-Python helpers (_embedding_model, _reid_gallery) importable without
rclpy — 18/18 unit tests pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:39:21 -05:00
03e7995e66 Merge pull request 'feat(jetson): CPU/GPU thermal monitor — sysfs + /saltybot/thermal JSON (Issue #205)' (#209) from sl-jetson/issue-205-thermal into main 2026-03-02 11:39:03 -05:00
1600691ec5 Merge pull request 'feat(controls): node watchdog monitor (Issue #203)' (#207) from sl-controls/issue-203-watchdog into main 2026-03-02 11:38:55 -05:00
58bb5ef18e feat(jetson): CPU/GPU thermal monitor — sysfs + /saltybot/thermal JSON (Issue #205)
New saltybot_thermal package with thermal_node: reads all
/sys/class/thermal/thermal_zone* sysfs entries (millidegrees→°C),
publishes /saltybot/thermal JSON at 1 Hz with zones[], max_temp_c,
warn, and throttled flags. Logs ROS2 WARN at ≥75°C, ERROR at ≥85°C.
thermal_root param allows sysfs override for offline testing.
50/50 tests passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:21:18 -05:00
e247389b07 feat: Add Issue #203 - Node watchdog monitor (20Hz heartbeat detection)
Implements node watchdog ROS2 node that monitors heartbeats from critical
systems and triggers safety fallback when motor driver is lost >2s.

Features:
  - Monitor heartbeats from: balance, motor_driver, emergency, docking
  - Alert on /saltybot/node_watchdog (JSON) if heartbeat lost >1s
  - Safety fallback: zero cmd_vel if motor driver lost >2s
  - Republish cmd_vel on /saltybot/cmd_vel_safe with safety checks
  - 20Hz monitoring and publishing frequency
  - Configurable heartbeat timeout thresholds

Heartbeat Topics:
  - /saltybot/balance_heartbeat (std_msgs/UInt32)
  - /saltybot/motor_driver_heartbeat (std_msgs/UInt32)
  - /saltybot/emergency_heartbeat (std_msgs/UInt32)
  - /saltybot/docking_heartbeat (std_msgs/UInt32)
  - /cmd_vel (geometry_msgs/Twist)

Published Topics:
  - /saltybot/node_watchdog (std_msgs/String) - JSON status
  - /saltybot/cmd_vel_safe (geometry_msgs/Twist) - Safety-checked velocity

Package: saltybot_node_watchdog
Entry point: node_watchdog_node
Launch file: node_watchdog.launch.py

Tests: 20+ unit tests covering:
  - Heartbeat reception and timeout detection
  - Motor driver critical timeout (>2s)
  - Safety fallback logic
  - cmd_vel zeroing on motor driver loss
  - Health status JSON serialization
  - Multi-node failure scenarios

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 11:17:19 -05:00
bfd58fc98c Merge pull request 'feat(social): robot mesh comms — peer announce + person handoff (Issue #171)' (#202) from sl-jetson/issue-171-mesh-comms into main
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 2s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
2026-03-02 11:17:03 -05:00
bc45208768 feat: Add Issue #194 - Speed limiter node (50Hz safety constraints)
Implements speed limiter ROS2 node that enforces safety constraints from:
  - Terrain type (via /saltybot/terrain_speed_scale)
  - Battery level (via /saltybot/speed_limit)
  - Emergency system state (via /saltybot/emergency)

Node computes minimum scale factor and applies to /cmd_vel, forwarding
limited commands to /saltybot/cmd_vel_limited. Publishes JSON telemetry
on /saltybot/speed_limit_info at 50Hz (20ms cycle).

Features:
  - Subscription to terrain, battery, and emergency constraints
  - Twist velocity scaling with min-of-three constraint logic
  - JSON telemetry with timestamp and all scale factors
  - 50Hz timer-based publishing for real-time control
  - Emergency state mapping (NOMINAL/RECOVERING/STOPPING/ESCALATED)
  - Comprehensive unit tests (18 test cases)

Package: saltybot_speed_limiter
Entry point: speed_limiter_node
Launch file: speed_limiter.launch.py

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
2026-03-02 11:14:10 -05:00
e5236f781b feat(social): robot mesh comms — peer announce + person handoff (Issue #171)
Some checks failed
social-bot integration tests / Lint (flake8 + pep257) (push) Failing after 9s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (push) Has been skipped
social-bot integration tests / Lint (flake8 + pep257) (pull_request) Failing after 9s
social-bot integration tests / Core integration tests (mock sensors, no GPU) (pull_request) Has been skipped
social-bot integration tests / Latency profiling (GPU, Orin) (push) Has been cancelled
social-bot integration tests / Latency profiling (GPU, Orin) (pull_request) Has been cancelled
New MeshPeer.msg (1 Hz DDS heartbeat: robot_id, social_state, active persons,
greeted names) and MeshHandoff.msg (person context transfer on STATE_LEAVING).
mesh_comms_node subscribes to person_states and orchestrator/state, publishes
announce heartbeat, triggers handoff on LEAVING, tracks peers with timeout
cleanup, and propagates mesh-wide greeting deduplication via /social/mesh/greeted.
73/73 tests passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 11:14:00 -05:00