Muazzam wrote:
As you know, companies like Tesla, Google, etc. are literally investing billions in developing autonomous vehicles.
Muazzam wrote:
I believe, that's self-evident that a hobby project, that someone develops just for their pleasure, is more perfect than a commercial project that a company develops for the project and people develop for their salaries.
Of course, you can waste your money as you wish, but it always be a failure. Just read your words - they spent billions. And they have required knowledge while you don't.
Muazzam wrote:
Here are my specifications for the project:
...
(2) Then you'll use an Arduino OR Raspberry Pi, OR even an x86 laptop to control it. (Mounted on the car.)
Yes, Arduino is just a perfect thing for autonomous cars. Just like calc.exe is a perfect tool for every rocket science PhD holder.
Sorry, but you just do not understand what the autonomous car is. Computer vision requires a lot of processing power. And it requires a lot of very smart algorithms. And there's not only computer vision involved with the autonomous cars. And every piece involved requires very smart algorithms. And many pieces require a lot of processing power. And finally - all the pieces require a person who is experienced enough to connect the pieces and create the car. Now you can make a list of requirements and think about what part of it you really can do. But remember - a typical contemporary car has about 100 microcontrollers while it's still too far from something like "autonomous".
If it's not enough to stop you, then, of course, you can try. And after a few months you'll stop it anyway. But if you really have some money, it would be better to hire somebody with at least robotics engineering degree. And even then your project will be too far from something like the big corporations do. So, you can try, but at least you are warned.