ROS2 Jetson Cleaning Robot

I am building a fully-autonomous vacuuming robot around a Jetson Nano and a 3-D LiDAR and need an experienced ROS 2 developer to take it from a proof-of-concept chassis to a reliable household machine.

Core capabilities I’m after
• Vacuuming as the single cleaning function
• ROS 2 Navigation stack for path planning, live re-planning and return-to-dock
• Real-time obstacle avoidance fused from the LiDAR and the onboard IMU
• SLAM or comparable mapping so the robot can save, edit and reload floor maps between sessions

The hardware is already on hand: Jetson Nano, 3-D LiDAR, motor controller, wheel encoders, IMU and a basic suction module. Your job is to wire up the software side, tune the parameters for smooth coverage, and expose a simple YAML/JSON config so I can tweak speeds, suction modes and cleaning zones without recompiling.

Deliverables
1. Docker-based ROS 2 workspace with clean builds on Humble or Iron
2. Launch files that bring up mapping, navigation and obstacle layers in the correct order
3. Parameter set tuned on my sample apartment map (I will provide the bag files)
4. Documentation and short video demo showing the robot starting, mapping, vacuuming an area and docking automatically

Acceptance criteria
• Robot finishes a 25 m² environment with >95 % coverage on the logged costmap
• No collision above 2 cm error margin in three consecutive runs
• Map is saved, reloaded and reused on the next power-cycle without manual intervention

If you have prior work with Nav2, RTAB-Map, cartographer or similar stacks on embedded NVIDIA boards, please share a brief example. I can test firmware updates nightly and give rapid feedback, so iterative delivery is welcome.