A project with Jetson Nano

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

Hello everyone!

Very soon I will be participating in the robotics Olympiad. I have two ideas that I can implement with Jetson Nano.

  1. the Robot rides from the gamepad + object recognition (I roughly know how to do it)
  2. I need to come up with something where ‘value’ will be . Honestly, I don’t know what can be implemented for this.

What do you think, is it worth coming up with something from the second option or the first option is not bad, in order to show the public?

What can you advise for the second way?

Will the Raspberry PI Camera v2 be suitable for my tasks?

For some, this question may seem silly, I’m sorry, but I’m still new to this and may not know some basic concepts.
If there are any syntax errors, please forgive me. Still, there is a language barrier.

Thank you all!

2

Hi loksaws, welcome to the Jetson community! Can you explain more what you mean by ‘value’? Is it an object or artifact that you wish to locate? In that case, you should be able to use object detection DNN:

It’s recommended to start with SSD-Mobilenet or SSD-Inception pretrained on COCO dataset (which the above examples provide). So perhaps your ‘value’ or object could be one of the items from this list of 90 object classes included in the COCO dataset:

https://github.com/dusty-nv/jetson-inference/blob/master/data/networks/ssd_coco_labels.txt

Yes, rPI Camera Module v2 or a USB webcam like Logitech C920 or C270 would be good cameras to start with on Nano.

For inspiration, you can find some Jetson projects from the community posted here: