Jump to content

Building autonomous robots for racing as a summer project.

Hi,

 

I know that the title may not be the best description of what I'm trying to accomplish but hear me out.

Me and few friends decided that we are going to have a competition in building the best autonomous racing robot.

Our goal is to build a large obstacle course, set a general route through it and let our robots make the most efficient and fastest path while avoiding obstacles.

All of this is supposed to happend outdoors in area which size equates to around 100 m2.

We are not complete noobies in making autonomous stuff and all have experience in machine learning, small electronics , motors etc.

But one thing we disagree about is the requirements for our outside navigation systems.

 

We are having trouble choosing between normal cameras,stereo cams, lidar, gps, ultrasonic sensors, all of those??

Even tho our project is complicated we are still trying to keep our costs down.

So I'm looking for an advice from someone with more experience.

What combinations or a singular part should we choose as our navigation+obstacle detection system for our project?

 

I'm really looking forward to your answers.

Thank you.

 

Link to comment
Share on other sites

Link to post
Share on other sites

A lidar is a must for a project like this. You can complement it with a camera if you need to spot 2d points of reference for orientation or if you need to see colors (there are color lidars but they're quite expensive). avoid gps, it's not nearly precise enough for robot navigation.

Don't ask to ask, just ask... please 🤨

sudo chmod -R 000 /*

Link to comment
Share on other sites

Link to post
Share on other sites

SparkFun previously held an annual contest called the Autonomous Vehicle Competition. Research that as it is extremely similar to what you are trying to do. I assume somewhere out there on the web is information regarding past participants and what they built.

Link to comment
Share on other sites

Link to post
Share on other sites

Two cameras (a software stereo camera in the end) and a jetson nano should be enough for what you want.

 

Lidar would make it too easy and is kinda overkill IMO.

 

If you really wanna make it a nice challenge, have all of those and make a model efficient enough to run in a SBC, maybe something not as powerful as a Jetson.

FX6300 @ 4.2GHz | Gigabyte GA-78LMT-USB3 R2 | Hyper 212x | 3x 8GB + 1x 4GB @ 1600MHz | Gigabyte 2060 Super | Corsair CX650M | LG 43UK6520PSA
ASUS X550LN | i5 4210u | 12GB
Lenovo N23 Yoga

Link to comment
Share on other sites

Link to post
Share on other sites

Thank you all for the help. I will certainly take a look at your suggestions.

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×