sl-jetson
c44a30561a
New package: saltybot_perception
person_detector_node.py:
- Subscribes /camera/color/image_raw + /camera/depth/image_rect_raw
(ApproximateTimeSynchronizer, slop=50ms)
- Subscribes /camera/color/camera_info for intrinsics
- YOLOv8n inference via TensorRT FP16 engine (Orin Nano 67 TOPS)
Falls back to ONNX Runtime when engine not found (dev/CI)
- Letterbox preprocessing (640x640), YOLOv8n post-process + NMS
- Median-window depth lookup at bbox centre (7x7 px)
- Back-projects 2D pixel + depth to 3D point in camera frame
- tf2 transform to base_link (fallback: camera_color_optical_frame)
- Publishes:
/person/detections vision_msgs/Detection2DArray all persons
/person/target geometry_msgs/PoseStamped tracked person 3D
/person/debug_image sensor_msgs/Image (optional)
tracker.py — SimplePersonTracker:
- Single-target IoU-based tracker
- Picks closest valid person (smallest depth) on first lock
- Re-associates across frames using IoU threshold
- Holds last known position for configurable duration (default 2s)
- Monotonically increasing track IDs
detection_utils.py — pure helpers (no ROS2 deps, testable standalone):
- nms(), letterbox(), remap_bbox(), get_depth_at(), pixel_to_3d()
scripts/build_trt_engine.py:
- Converts ONNX to TensorRT FP16 engine using TRT Python API
- Prints trtexec CLI alternative
- Includes YOLOv8n download instructions
config/person_detection_params.yaml:
- confidence_threshold: 0.40, min_depth: 0.5m, max_depth: 5.0m
- track_hold_duration: 2.0s, target_frame: base_link
launch/person_detection.launch.py:
- engine_path, onnx_path, publish_debug_image, target_frame overridable
Tests: 26/26 passing (test_tracker.py + test_postprocess.py)
- IoU computation, NMS suppression, tracker state machine,
depth filtering, hold duration, re-association, track ID
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.