Computing Value - Artificial Intelligence for Robotics Udacity English Japanese

Computing Value - Artificial Intelligence for RoboticsYouTube↗ IA↗(long shot)
Education 8.1K views 2 likes 0 dislikes 30 May 2012

Udacity 651K subscribers United States YouTube↗

Click to Play Video

Let's look at a very simple piece of code that implements this planning algorithm.

この計画アルゴリズムを実装するシンプルなコードを見てみましょう

We have a grid here as before with 0s and 1s. You're familiar with it.

前回と同様ゼロと1を持つグリッドがあります見覚えがありますね

The start location on the top left, the goal location on the bottom right.

出発地は左上でゴールは右下です

We can set up arbitrary obstacles like a wall over here and a wall over here

壁などの任意の障害物をここやここに配置でき

that forces the robot into kind of an S-curve around the corner.

ロボットは角で S字カーブを描かざるを得なくなります

If I run this code with this table, what I get is a table that looks like this.

この表でコードを実行すると取得する表はこのようになります

This for each of the states that is a non-wall state.

この状態はそれぞれ壁のない状態です

It tells me what's the optimal thing to do.

この表から最適な動作が分かります

So over here it says go south. Here is says go right. Here is says go up.

ここは南に行けと言っていますここは右へそして上へ

Here is says go right again and go south.

再び右、南へ行けと言っています

Realize that even states I'm not likely to every reach,

絶対に到達しないであろう状態のこれらの位置でも関連する

like the one over here and the on over here, have an optimal policy

最適なポリシーと行動があります

and action associated, because there is really no start state. There is just a goal state over here.

それは出発状態が存在せずゴール状態があるだけだからです

The specification of the initial state has no bearing on this result.

初期状態の指定はこの結果に影響しません

How can we compute this efficiently?

どうすればこれを効率良く計算できるでしょうか？

Let me make a simple example of a world like this with an obstacle over here.

簡単な例としてここに障害物のある世界の例を挙げてみましょう

Say our goal state is the one in the corner over here.

ゴール状態はこの角だとします

Rather than telling you how to compute the optimal policy, which assigns an action to each of these cells,

これらの各セルに動作を割り当てる最適なポリシーを計算する方法を説明するのではなく

let me instead teach you about "value."

価値について説明しましょう

A "value function" associates to each grid cell the length of the shortest path to the goal.

価値関数は各グリッドセルにゴールまでの最短経路の距離を関連づけます

For the goal, obviously, it is 0.

ゴールの場合は当然ゼロです

For each adjacent cell to the goal, it's obviously 1.

ゴールの隣の各セルは1です

For the guys over here, 2, 3, 4, 5, 6, and 7.

ここは2、3、4、5、6、7です

This is recursively calculated by taking the optimal neighbor x-prime, y-prime,

これは隣接する最適なx’とy’を取ってその価値を考慮して再帰的に計算されます

considering its value, and by adding the costs it takes to get there,

そしてそこに行くまでのコストを加算します

which in our example will be plus 1.

私たちの例ではプラス1になります

By applying this update equation recursively,

この更新の方程式を再帰的に適用することで

we can attain this value function over here.

この価値関数を実現することができます

Once we have this value function, we find that the optimal control action is obtained by minimizing the value, which is a hill-climbing type of action.

この価値関数が得られれば最適な制御動作が価値の最小化によって得られることが分かりますこれは山登りのような動作です

Let me give you a quiz.

では小テストを出しましょう

In this world here with the goal location over here,

この世界でゴールがここにある場合

I'd like to understand what is the value of the cell in the bottom right.

右下のセルの価値はいくつでしょうか？

Similar videos:

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

Kalman Filter Code - Artificial Intelligence for Robotics
Udacity
41K views 44 likes 0 dislikes 29 May 2012100% match

Programming Exercise - Artificial Intelligence for Robotics
Udacity
35.6K views 144 likes 6 dislikes 23 Feb 2015100% match

Circular Motion - Artificial Intelligence for Robotics
Udacity
17.2K views 19 likes 2 dislikes 23 Feb 2015100% match

Shifting the Mean - Artificial Intelligence for Robotics
Udacity
15.9K views 7 likes 2 dislikes 29 May 2012100% match

Localization Program - Artificial Intelligence for Robotics
Udacity
31K views 68 likes 0 dislikes 02 Mar 2012100% match

Inexact Motion 3 - Artificial Intelligence for Robotics
Udacity
15K views 6 likes 1 dislikes 19 Feb 2012100% match

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

Parameter Update - Artificial Intelligence for Robotics
Udacity
28.7K views 5 likes 3 dislikes 29 May 2012100% match

Maximize Gaussian - Artificial Intelligence for Robotics
Udacity
16.9K views 6 likes 0 dislikes 29 May 2012100% match

Gaussian Intro - Artificial Intelligence for Robotics
Udacity
8.9K views 8 likes 1 dislikes 29 May 2012100% match

Normalized Sense Function - Artificial Intelligence for Robotics
Udacity
17.7K views 8 likes 0 dislikes 19 Feb 2012100% match

Localization - Artificial Intelligence for Robotics
Udacity
7.4K views 6 likes 2 dislikes 02 Mar 2012100% match

Limit Distribution Quiz - Artificial Intelligence for Robotics
Udacity
14.6K views 10 likes 0 dislikes 19 Feb 2012100% match

PD Controller - Artificial Intelligence for Robotics
Udacity
22.3K views 21 likes 1 dislikes 30 May 2012100% match

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

Sensing - Artificial Intelligence for Robotics
Udacity
6.4K views 1 likes 0 dislikes 23 Feb 2015100% match

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

Formal Definition of Probability 3 - Artificial Intelligence for Robotics
Udacity
11.5K views 5 likes 0 dislikes 19 Feb 2012100% match

Implement P Controller - Artificial Intelligence for Robotics
Udacity
13.7K views 7 likes 0 dislikes 30 May 2012100% match

A* in Action - Artificial Intelligence for Robotics
Udacity
21.4K views 236 likes 2 dislikes 30 May 2012100% match

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

First Search Program - Artificial Intelligence for Robotics
Udacity
10.3K views 11 likes 1 dislikes 29 May 2012100% match

Implementing SLAM - Artificial Intelligence for Robotics
Udacity
16.5K views 30 likes 1 dislikes 31 May 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

Path Smoothing - Artificial Intelligence for Robotics
Udacity
18.2K views 35 likes 0 dislikes 30 May 2012100% match

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

pHit and pMiss - Artificial Intelligence for Robotics
Udacity
21.4K views 6 likes 2 dislikes 19 Feb 2012100% match

Gaussian Motion - Artificial Intelligence for Robotics
Udacity
15.5K views 8 likes 0 dislikes 29 May 2012100% match

Settings Privacy About Contact Donate