sl-perception
042c0529a1
Implements a 5-mode FSM for dynamic sensor activation based on speed,
scenario, and battery level — avoids running all 4 CSI cameras + full
sensor suite when unnecessary, saving ~1 GB RAM and significant compute.
Five modes (sensor sets):
SLEEP — no sensors (~150 MB RAM)
SOCIAL — webcam only (~400 MB RAM, parked/socialising)
AWARE — front CSI + RealSense + LIDAR (~850 MB RAM, indoor/<5km/h)
ACTIVE — front+rear CSI + RealSense + LIDAR + UWB (~1.15 GB, 5-15km/h)
FULL — all 4 CSI + RealSense + LIDAR + UWB (~1.55 GB, >15km/h)
Core library — _camera_power_manager.py (pure Python, no ROS2 deps)
- CameraPowerFSM.update(speed_mps, scenario, battery_pct) → ModeDecision
- Speed-driven upgrades: instant (safety-first)
- Speed-driven downgrades: held for downgrade_hold_s (default 5s, anti-flap)
- Scenario overrides (instant, bypass hysteresis):
· CROSSING / EMERGENCY → FULL always
· PARKED → SOCIAL immediately
· INDOOR → cap at AWARE (never ACTIVE/FULL indoors)
- Battery low cap: battery_pct < threshold → cap at AWARE
- Idle timer: near-zero speed holds at AWARE for idle_to_social_s (30s)
before dropping to SOCIAL (avoids cycling at traffic lights)
ROS2 node — camera_power_node.py
- Subscribes: /saltybot/speed, /saltybot/scenario, /saltybot/battery_pct
- Publishes: /saltybot/camera_mode (CameraPowerMode, latched, 2 Hz)
- Publishes: /saltybot/camera_cmd/{front,rear,left,right,realsense,lidar,uwb,webcam}
(std_msgs/Bool, TRANSIENT_LOCAL so late subscribers get last state)
- Logs mode transitions with speed/scenario/battery context
Tests — test/test_camera_power_manager.py: 64/64 passing
- Sensor configs: counts, correct flags per mode, safety invariants
- Speed upgrades: instantaneous at all thresholds, no hold required
- Downgrade hysteresis: hold timer, cancellation on speed spike, hold=0 instant
- Scenario overrides: CROSSING/EMERGENCY/PARKED/INDOOR, all CSIs on crossing
- Battery low: cap at AWARE, threshold boundary
- Idle timer: delay AWARE→SOCIAL, motion resets timer
- Reset, labels, ModeDecision fields
- Integration: full ride scenario (walk→jog→sprint→crossing→indoor→park→low bat)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Jetson Nano — AI/SLAM Platform Setup
Self-balancing robot: Jetson Nano dev environment for ROS2 Humble + SLAM stack.
Stack
| Component | Version / Part |
|---|---|
| Platform | Jetson Nano 4GB |
| JetPack | 4.6 (L4T R32.6.1, CUDA 10.2) |
| ROS2 | Humble Hawksbill |
| DDS | CycloneDDS |
| SLAM | slam_toolbox |
| Nav | Nav2 |
| Depth camera | Intel RealSense D435i |
| LiDAR | RPLIDAR A1M8 |
| MCU bridge | STM32F722 (USB CDC @ 921600) |
Quick Start
# 1. Host setup (once, on fresh JetPack 4.6)
sudo bash scripts/setup-jetson.sh
# 2. Build Docker image
bash scripts/build-and-run.sh build
# 3. Start full stack
bash scripts/build-and-run.sh up
# 4. Open ROS2 shell
bash scripts/build-and-run.sh shell
Docs
docs/pinout.md— GPIO/I2C/UART pinout for all peripheralsdocs/power-budget.md— 10W power envelope analysis
Files
jetson/
├── Dockerfile # L4T base + ROS2 Humble + SLAM packages
├── docker-compose.yml # Multi-service stack (ROS2, RPLIDAR, D435i, STM32)
├── README.md # This file
├── docs/
│ ├── pinout.md # GPIO/I2C/UART pinout reference
│ └── power-budget.md # Power budget analysis (10W envelope)
└── scripts/
├── entrypoint.sh # Docker container entrypoint
├── setup-jetson.sh # Host setup (udev, Docker, nvpmodel)
└── build-and-run.sh # Build/run helper
Power Budget (Summary)
| Scenario | Total |
|---|---|
| Idle | 2.9W |
| Nominal (SLAM active) | ~10.2W |
| Peak | 15.4W |
Target: 10W (MAXN nvpmodel). Use RPLIDAR standby + 640p D435i for compliance.
See docs/power-budget.md for full analysis.