Parameter Optimization - Artificial Intelligence for Robotics Udacity English Japanese

Parameter Optimization - Artificial Intelligence for RoboticsYouTube↗ IA↗(long shot)
Education 11.7K views 8 likes 0 dislikes 18 Mar 2012

Udacity 651K subscribers United States YouTube↗

Click to Play Video

So to implement this I’ve modified the RAN procedure to input a parameter vector of three

3つのパラメータのパラメータベクトルを入力するようにrunプロシージャを修正しました

parameters. And for reasons that will be obvious later, I have a print flag that I default to false.

理由はあとで説明しますがデフォルトでFalseのprintflagを設けました

I have the same initial parameters as before, speed and arrow cross stick arrow – into the

前回と同じ初期パラメータのspeed、err、 crosstrack＿error、int＿crosstrack＿error、

cross stick arrow, I set my fifth parameter

5番目のパラメータを設定し

and to make it a little bit more obvious how what the effect of parameter selection has on

パラメータ選択の効果が誤差にどう影響するかもう少し明らかにするようにします

my arrow. I also set the total number equations to N times 2 and when I count the total cross stick arrow, I only counted from step N 1,

総数の式をN＊2に設定します crosstrack＿errorの総和を求めるにはステップNから数えればいいだけです

so I give the algorithm a chance to convert to zero for N steps, they don’t count the cross

アルゴリズムがNステップを0へ変換させるので crosstrack＿errorは計算しません

stick arrow, but like to know how the cross stick arrow evolves quite dramatically from step 101 on to 200. If the print flag is set, I set the output here in degrees and not in variance

ステップ101から200までにcrosstrack＿errorがどう劇的に変化するか知りたいのです printflagが設定されていればラジアンではなく度数で出力するように設定しました

and I return my average arrow before value.

ここでerrの平均を返します

So I wanted to write the routine twiddle and

ではいじり回しのルーチンを書きましょう

the routine should find the optimal parameters

最適なパラメータを見つけてそれらを返すルーチンです

and return them to me. So I want you to implement the twiddle with a tolerance and threshold of 0.001. In one twiddle, it shows the parameters over time and the cross

閾値と許容値が0．001である twiddleを実装してください twiddleではパラメータとクロストラックエラーが出力されます

stick arrow. And this cross stick arrow very quickly goes to zero. In fact after a

クロストラックエラーはすぐに0になります

few iterations, 107 in my implementation

何回か繰り返すと私の実装では107番目で

we get a cross stick arrow of 3.611 to the

クロストラックエラーが 3．611×10⁻¹⁷になりました

minus 17th. And here is the typical control one, you see my X, my Y, my orientation,

典型的な制御の出力があります位置x、y、方向があり

my drift is constant, that’s my constant drift parameters and the beginning of the

ドリフトは一定ですこれは一定のドリフトのパラメータです

arrows are 195 on average. But after a short

初期の誤差は平均で195です

amount of time, you find that my Y arrow goes down to 10 to the minus 6 and stays

しかし時間が少し過ぎるとyの誤差が 10⁻⁶に減ることが分かります

there, which means our controller is really,

そして減ったままになります

really good in tracking our desired location.

コントローラが目標位置の追跡においていい結果を出している証拠です

In our final control error between time step 100 and 200 is 3.611. So I wanted to

時間ステップが100から200の間の最終的な制御誤差は3．611です

implement twiddle, we might change something

いじり回しを実装したかったのでこれまでの設定を変えるかもしれませんが

on the vowel set up, but when you run it, it will be such that if you want a full PED

実行すればPIDコントローラで使える最適なパラメータが分かるでしょう

controller and find the optimal parameters that the final control error, will be really, really small and that’s how we’ll checking.

最終的な制御誤差は確認したようにかなり小さくなるはずです

Similar videos:

Expansion Grid - Artificial Intelligence for Robotics
Udacity
10.4K views 2 likes 0 dislikes 29 May 2012100% match

Exact Motion - Artificial Intelligence for Robotics
Udacity
15.1K views 12 likes 1 dislikes 19 Feb 2012100% match

Two Coin Quiz - Artificial Intelligence for Robotics
Udacity
12.3K views 7 likes 0 dislikes 19 Feb 2012100% match

Twiddle - Artificial Intelligence for Robotics
Udacity
13.8K views 64 likes 2 dislikes 18 Mar 2012100% match

Belief Modality - Artificial Intelligence for Robotics
Udacity
9.7K views 9 likes 0 dislikes 29 May 2012100% match

Inexact Move Function - Artificial Intelligence for Robotics
Udacity
17.3K views 10 likes 0 dislikes 19 Feb 2012100% match

Print Path - Artificial Intelligence for Robotics
Udacity
10.2K views 3 likes 0 dislikes 29 May 2012100% match

Add Noise - Artificial Intelligence for Robotics
Udacity
11.4K views 6 likes 0 dislikes 29 May 2012100% match

New Particle - Artificial Intelligence for Robotics
Udacity
11.5K views 5 likes 0 dislikes 29 May 2012100% match

Inexact Motion 1 - Artificial Intelligence for Robotics
Udacity
11.2K views 15 likes 0 dislikes 19 Feb 2012100% match

Kalman Prediction - Artificial Intelligence for Robotics
Udacity
10.5K views 6 likes 1 dislikes 29 May 2012100% match

Predict Function - Artificial Intelligence for Robotics
Udacity
15.2K views 4 likes 0 dislikes 29 May 2012100% match

Formal Definition of Probability 1 - Artificial Intelligence for Robotics
Udacity
13K views 9 likes 2 dislikes 19 Feb 2012100% match

Proportional Control - Artificial Intelligence for Robotics
Udacity
8.8K views 8 likes 0 dislikes 30 May 2012100% match

Kalman Filter Design
Udacity
21K views 84 likes 12 dislikes 29 May 2012100% match

Test Sense Function - Artificial Intelligence for Robotics
Udacity
28.8K views 13 likes 0 dislikes 19 Feb 2012100% match

Planning Solution - Artificial Intelligence for Robotics
Udacity
620 views 0 likes 0 dislikes 16 Mar 2012100% match

Compute Sum - Artificial Intelligence for Robotics
Udacity
30.2K views 12 likes 0 dislikes 19 Feb 2012100% match

Separated Gaussians - Artificial Intelligence for Robotics
Udacity
22.9K views 13 likes 0 dislikes 29 May 2012100% match

Preferred Gaussian - Artificial Intelligence for Robotics
Udacity
15.7K views 1 likes 0 dislikes 29 May 2012100% match

Moving Robot - Artificial Intelligence for Robotics
Udacity
22.1K views 14 likes 0 dislikes 29 May 2012100% match

Move Twice - Artificial Intelligence for Robotics
Udacity
14.9K views 6 likes 0 dislikes 19 Feb 2012100% match

Cancer Test - Artificial Intelligence for Robotics
Udacity
23.3K views 11 likes 0 dislikes 19 Feb 2012100% match

Probability After Sense - Artificial Intelligence for Robotics
Udacity
16.3K views 18 likes 2 dislikes 19 Feb 2012100% match

Gradient Descent - Artificial Intelligence for Robotics
Udacity
96.4K views 628 likes 76 dislikes 21 Mar 2012100% match

Introduction - Artificial Intelligence for Robotics
Udacity
43.2K views 323 likes 6 dislikes 19 Feb 2012100% match

Resampling Wheel - Artificial Intelligence for Robotics
Udacity
11.4K views 14 likes 0 dislikes 29 May 2012100% match

Sense and Move 2 - Artificial Intelligence for Robotics
Udacity
14.5K views 7 likes 0 dislikes 19 Feb 2012100% match

Importance Weight - Artificial Intelligence for Robotics
Udacity
14.8K views 12 likes 1 dislikes 29 May 2012100% match

Uniform Distribution - Artificial Intelligence for Robotics
Udacity
37.2K views 19 likes 0 dislikes 19 Feb 2012100% match

Settings Privacy About Contact Donate