I am a college student who is entering my fourth year of university and, unfortunately, all I really know is theory. Now I want to build something and be relevant. So, I wanted to build an autonomous RC car that uses some sort of computer vision.
I have seen some recommendations about donkeycar and f1tenth.org, but I want the best of both worlds! I love the fact that f1tenth uses ROS and can potentially cover SLAM and other stuff that I don’t quite understand (yet)! So, I was wondering if it is possible to build a donkey car but make it go beyond beginner level? I was hoping to take this thing to an advanced level, and hopefully go as hard as what I see on f1tenth.
The stuff on f1tenth is SO EXPENSIVE ($1600 Hokuyo sensor and a $400 Nvidia Jetson TX2). Is it possible to use just a raspberry pi and progressively go more in depth? What are the pros and cons of building a donkeycar instead of one of the fancier cars? Is it worth getting a LiDAR sensor? Maybe I am in over my head, but I want to go deep on a project.
I hope to make this a fun place for discussion!