phe yeong kiang a152076. introduction for this course lmck1531 kepimpinan & kreativiti, i will...

17
LMCK1531 KEPIMPINAN & KREATIVITI PHE YEONG KIANG A152076

Upload: verity-green

Post on 14-Dec-2015

212 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

LMCK1531KEPIMPINAN & KREATIVITI

PHE YEONG KIANG

A152076

Page 2: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

Introduction

For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club.

Page 3: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

What I doing in the Robot Soccer's Club?

1. Calculate the angle of robot to shoot the ball.

2. Study some machine learning knowledge.

Page 4: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

Why I doing the task?

1. Because I want improve robot accuracy shooting the ball and reduce the process when robots shoot the ball.

2. Because I want improve robot learning technique.

Page 5: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

How I doing the task?

A.Improve robot accuracy shooting the ball.

State1: When camera get State2: The computer will the position ball and robot. calculate the angle for the ball to find the location for the robot.

Page 6: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

State3: The robot will change State4: The computer will the position to 0 degree.calculate the angle for robot to change the

position to shoot the ball.

Page 7: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

State5: Then the ball will be shot into the goal.

Page 8: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

How I doing the task?

B. Reduce the process when robots shoot the ball.

State1: When camera get State2: The computer will the position ball and robot. calculate the angle for the ball to find the location for the robot.

Page 9: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

State3: The computer will State4: Then the ball will be shot calculate the angle for robot into the goal.to direct change the position and shoot the ball, without change the position to 0 degree.

I already successfully completed the part A, but part B still exploring.

Page 10: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

Improve robot learning technique

I using the Q- Learning to try improve robot learning technique.

In fact, I have no any knowledge for Q-Learning, then I do a lot of investigation and to interrogate my seniors, finally I have some knowledge about the theory of Q- Learning. But in the meantime I was very upset, I asked the senior, senior said he did not know, because he never learned, so, I can only themselves to explore .

Now I show what I learned in this Q- Learning.

Page 11: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

This is the sample how the object get the state from start point to end point.

Page 12: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

AlgorithmState1: For each state-action pair (s, a), initialize the

table entry Qi(s, a) to zeroState2: Observe the current state sState3: Do forever: State3.1: Select an action a and execute itState3.2: Receive immediate reward rState3.3: Observe the new state s[new]State3.4: Update the table entry for Q[new](s, a)as

follows:Q[old](s ,a)=r + γ *maxa* Q[new](s ,a)s[old]=s[new]

Page 13: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

Q(s2, a23) = r + 0.5 * max(Q(s3,a32),Q(s3,a36))= 0 +0 .5 *0=0, 0 +0 .5 *0=0

Page 14: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

S6 is FINAL STATE soQ(s3, a36) = r = 100

Page 15: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

After the end point, the program will loop again until all the state get the value.

Q(s2, a23) = r + 0.5 * max(Q(s3,a32), Q(s3,a36))= 0 + 0.5 * 0 = 0, 0 + 0.5 * 100 = 50

Page 16: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

The is the output after all state get the value.And the next part is using neural network to

find the good way from start point to end point.

But this part I also exploring.

Page 17: PHE YEONG KIANG A152076. Introduction For this course LMCK1531 KEPIMPINAN & KREATIVITI, I will talk about what I've try to do in the Robot Soccer's Club

I believe these tasks will improve the robot system. And I feel happy because can try to do this task, and I will continue to explore these tasks.

Conclusion