Use of Huskylens to Detect Victims 2024

hi,

i read the response from Matej Profile - Matej - RoboCupJunior Forum RoboCupJunior Rescue Committee Member, an Nov 2022.

We live in a different world since that answer , so i would like you to reconsider the option of using Huskylens.

since answer in 2022 has been given - Chat-GPT and other generic AI are in intense use , CO-Pilot is “using” Codes of very good programmers and writing very nice codes and the tools are different. The most important thing is to teach the children to adopt new technologies and AI is here de-facto as a tool.

i think that if the children’s understand what they are doing, it should be alowd.

sincerely yours

Oded

I am not on the Technical Committee but I doubt they will allow it.

According to the description of the Huskylens… “Users can change various algorithms easily by pressing the function button.”

The videos they have do show it being trained for color and object detection just by pushing buttons and there doesn’t seem to be any programming whatsoever.

I have been mentoring RCJ teams for a while and the Technical Committee almost always rejects these devices. They will allow cameras to be trained but some form of programming normally has to take place. For example, OpenCV or OpenMV cameras are allowed because there is normally some programming that must happen to make it work.

The children have to do some programming… your analogy of ChatGPT doesn’t really work. What do the children learn except that they can get an AI Bot to do the coding for them?

Again I am not on the TC so you should wait to hear from them.

Huskey Lens Wiki

Hi @oded.val,

Please refer to rule 3.2.2. “Teams are not permitted to use commercially produced robot kits or sensors components specifically designed or marketed to complete any single primary task of RoboCupJunior Rescue.” Using the camera’s own object detection software to detect victims would undoubtedly violate this rule.

If you are a mentor, could you please share what your students understand from your perspective? What kind of technical reserve, knowledge base is required of them to use a camera with its own software? What techniques can they acquire in the process of using it? We’re planning to add restrictions on similar software to the rules, and we’d benefit greatly from feedback from the community!

Ranyi
2024 committee

Hi,
The children’s point is that more and more devices are black boxes and in this era the objective is to learn to use the objects as in
OO programming.
They don’t write the software for bio fingerprint recognition or leader or RFID, , they are using libraries and codes written by the manufacturer as OO would sugests.
Therefore they want us to give them new challenges, instead of forcing them to work with all the technologies.
From my point of view it is very beneficial to write a c compiler or to know how to do a square root without a calculator, but that should not be the main focus of robotics , in the era of generic AI.
For the now generation, I would change the the challenge every year or two, in order to avoid copy paste from earlier years ,especially when they know that the college teams are revealing their codes and solutions on the web.
I would like to know if you can relay to any of the above.
Sincerely yours,
Oded

It should have been LIDAR instead of leader of course :laughing:.