OCCRA
Go to Post The Glass is Half Full - Optimist.......The Glass is Half Empty - Pessimist.......The Glass is too Big - Engineer - mpking [more]
Home
Go Back   Chief Delphi > Technical > Technical Discussion
CD-Media   CD-Spy  
portal register members calendar search Today's Posts Mark Forums Read FAQ rules

 
Reply
Thread Tools Rate Thread Display Modes
  #1   Spotlight this post!  
Unread 09-18-2018, 06:59 PM
brad.harker's Avatar
brad.harker brad.harker is offline
Registered User
FRC #5546 (A.R.T.)
Team Role: Programmer
 
Join Date: Jan 2017
Rookie Year: 2017
Location: Petersburg, Virginia
Posts: 6
brad.harker is an unknown quantity at this point
Deep Learning/Neural Network Use In Scouting

Hi, I'm a real beginner with deep learning and I've only messed around with it a small amount. So I've seen other teams out here with full scouting applications with predictive deep learning algorithms to predict match results. A lot of this seems completely overwhelming so I was wondering (maybe this will be helpful to others looking as well) if you guys have seen any good resources for getting into deep learning in an FRC Scouting environment? Thanks so much!
Reply With Quote
  #2   Spotlight this post!  
Unread 09-18-2018, 07:28 PM
cgund98 cgund98 is offline
Registered User
AKA: Callum Gundlach
FRC #1747
Team Role: CAD
 
Join Date: Feb 2018
Rookie Year: 2016
Location: Lafayette, Indiana
Posts: 9
cgund98 is a glorious beacon of lightcgund98 is a glorious beacon of lightcgund98 is a glorious beacon of lightcgund98 is a glorious beacon of lightcgund98 is a glorious beacon of lightcgund98 is a glorious beacon of light
Re: Deep Learning/Neural Network Use In Scouting

Deep learning is a niche that takes a good amount of attention to grasp. The most important thing for a neural network is the data, which is, in my opinion, where the problem is in the FRC environment. While you can collect performance data for each match, it is hard to narrow robot characteristics down to a data point. Models need good, solid data. The more info the better.

That being said, I wish you luck in your ventures. You have to start of with the basics and work your way up. I personally took Andrew Ng's ML course on Coursera and then loved Practical Deep Learning for Coders from fast.ai.

You can find more courses from articles like this

Good luck!
Reply With Quote
  #3   Spotlight this post!  
Unread 09-18-2018, 07:29 PM
WaydeG WaydeG is offline
Registered User
FRC #2102
Team Role: Leadership
 
Join Date: Aug 2015
Rookie Year: 2015
Location: California
Posts: 4
WaydeG is an unknown quantity at this point
Re: Deep Learning/Neural Network Use In Scouting

Check out part 1 of Fastai's MOOC. I developed all the predicted match scores/robot stats features for my team's (Team 2102) scouting application last year using key principles from this course. I suggest that you've got a decent background in high school math, Python, and a willingness to learn/struggle with new concepts as you go into the course as it took me a few times to go through all the lessons to really understand what I was doing. I'm actually working on a write up right now on how we developed our scouting application RoboRecon which includes all the ML/Deep Learning work. PM me if you've got more questions.

-Wayde
Reply With Quote
  #4   Spotlight this post!  
Unread 09-18-2018, 10:15 PM
solomondg's Avatar
solomondg solomondg is offline
Registered User
AKA: Solomon
FRC #2898 (Flying Hedgehogs)
Team Role: Leadership
 
Join Date: Aug 2016
Rookie Year: 2016
Location: Portland, Oregon
Posts: 110
solomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant futuresolomondg has a brilliant future
Re: Deep Learning/Neural Network Use In Scouting

There's really not enough data out there to develop comprehensive predictions. I'd love to be proven wrong, but so far every scouting or prediction system I've seen that uses any sort of machine learning either produces highly inaccurate data, makes a _lot_ of assumptions (producing pretty but generally inaccurate data), or barely outperforms a simple OPR or win-loss rate comparison. Neural networks need a ton of data, and that data just isn't out there.
Reply With Quote
  #5   Spotlight this post!  
Unread 09-21-2018, 08:51 AM
Aaron Li's Avatar
Aaron Li Aaron Li is offline
Registered User
FRC #1665 (Weapons of Mass Construction)
Team Role: Driver
 
Join Date: Aug 2018
Rookie Year: 2017
Location: New York
Posts: 65
Aaron Li is an unknown quantity at this point
What do you mean by scouting? We have clipboards and printed sheets to scout all teams from auto to endgame. It's not 100% accurate as there can be a few misunderstandings and our scouters may not understand them. We collect these and look at them at the hotels, in the stands and the pits. We're usually forgiving on penalties but constant reoccurrence well be significant. But that's the way our scouting goes.

Sent from my Galaxy S8 using Tapatalk
Reply With Quote
  #6   Spotlight this post!  
Unread 09-21-2018, 09:57 AM
Hitchhiker 42's Avatar
Hitchhiker 42 Hitchhiker 42 is offline
Roboter
AKA: Mark Lavrentyev
no team (FullMetal Falcons)
Team Role: Programmer
 
Join Date: Oct 2015
Rookie Year: 2015
Location: Providence, RI
Posts: 992
Hitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond reputeHitchhiker 42 has a reputation beyond repute
Re: Deep Learning/Neural Network Use In Scouting

Quote:
Originally Posted by Aaron Li View Post
What do you mean by scouting? We have clipboards and printed sheets to scout all teams from auto to endgame. It's not 100% accurate as there can be a few misunderstandings and our scouters may not understand them. We collect these and look at them at the hotels, in the stands and the pits. We're usually forgiving on penalties but constant reoccurrence well be significant. But that's the way our scouting goes.
I think OP is talking about using the data you collected (by app, paper, scantron, whatever) to make match predictions/give picklists using deep learning.
__________________
Don't forget your towel!

Reply With Quote
  #7   Spotlight this post!  
Unread 09-21-2018, 10:39 AM
Poorva.Halbe's Avatar
Poorva.Halbe Poorva.Halbe is offline
Registered User
FRC #2502 (Talon Robotics)
Team Role: Driver
 
Join Date: Oct 2016
Rookie Year: 2012
Location: Eden Prairie
Posts: 6
Poorva.Halbe is an unknown quantity at this point
Re: Deep Learning/Neural Network Use In Scouting

We use tablets to get scouting data with an app, that later gets compiled into an excel spreadsheet. Our mentor works with statistics quite a bit (CD username "Whatever") and he made an extremely accurate FTC calculator a few years ago using algorithms which he then implemented last year for FRC. I'm sure if you have questions he could help!
Reply With Quote
  #8   Spotlight this post!  
Unread 09-21-2018, 01:36 PM
kpildner kpildner is offline
Registered User
FRC #4946 (Alpha Dogs)
Team Role: Parent
 
Join Date: Apr 2017
Rookie Year: 2017
Location: Bolton, Ontario, Canada
Posts: 6
kpildner is an unknown quantity at this point
Re: Deep Learning/Neural Network Use In Scouting

I have used the following data sources in the past to build predictive models. Both sources update and publish weekly on during the FIRST Robotics Season.

Caleb Sykes posts white papers and past season statistics, as well as a scouting database. Ether also publishes raw data and analysis.

Start with the White Papers published by Caleb: https://www.chiefdelphi.com/media/papers/3315

Caleb's scouting data base:
https://www.chiefdelphi.com/media/papers/3439

Ether's published raw data.
https://www.chiefdelphi.com/media/papers/3451

Good luck!

Kathleen
Reply With Quote
Reply


Thread Tools
Display Modes Rate This Thread
Rate This Thread:

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump


All times are GMT -5. The time now is 03:38 AM.

The Chief Delphi Forums are sponsored by Innovation First International, Inc.


Powered by vBulletin® Version 3.6.4
Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.
Copyright © Chief Delphi