simulator VS MissionPlanner

I've been trying for a while now and I started thinking it may not be possible. If anyone has managed to train a self-driving car simulator using openai gym on google colab(preferably), or on any remote server (AWS, GCP, ...) please let me know. So far, I tried carla, airsim, svl, deepdrive and they are all equally useless unless run locally with a gui. I'd really appreciate if someone suggests some way that actually can make it possible.

Run Mission Planner on a PC, connect it to your flight controller, go to "CONFIG", then "full parameter list", then type the first characters of the one you want in the search box on the right.

To add to this, most of the time one doesn't need to hack on the drone firmware itself. Just configuring/hacking the mission planner alone would go a long way: https://ardupilot.org/planner/

But if you're interested in more readable codebases without too much legacy headaches:

https://github.com/BossHobby/QUICKSILVER (for indoor drones mostly)

And for even less functionality but a good learning tool kind of codebase:

https://github.com/nickrehm/dRehmFlight

I want to build a gui to control a small autonomous boat. My initial plan was to modify this thing: https://github.com/ArduPilot/MissionPlanner

If you want to learn how to build it from scratch, you can still look at Arducopter for the firmware. It's entirely open source, including the GCS's like Mission Planner, and you can look at how they implement control over telemetry radios (using a protocol called Mavlink).

Related feature request, )elevation data from the Norwegian Mapping Authority ): https://github.com/ArduPilot/MissionPlanner/issues/2527