課程資訊
課程名稱
 機器人知覺與學習
ROBOT PERCEPTION AND LEARNING 
開課學期
 99-1 
授課對象
 電機資訊學院  資訊網路與多媒體研究所  
授課教師
 王傑智 
課號
 CSIE5117 
課程識別碼
 922EU3430 
班次
  
學分
 3 
全/半年
 半年 
必/選修
 選修 
上課時間
 星期四2,3,4(9:10~12:10) 
上課地點
 資105 
備註
 本課程以英語授課。本課程以英語授課。
限學士班三年級以上
總人數上限：30人 
Ceiba 課程網頁
 http://ceiba.ntu.edu.tw/991pal 
課程簡介影片
 
核心能力關聯
 核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

PRELIMINARIES
FUNDAMENTALS OF REAL VARIABLES
MATHEMATICAL PRELIMINARIES
FUNDAMENTALS OF UNCERTAINTY ANALYSIS
FUNDAMENTALS OF RANDOM PROCESSES

MARTINGALES, STOPPING TIMES AND FILTRATIONS
STOCHASTIC PROCESSES AND SIGMA FIELDS
STOPPING TIMES
CONTINUOUS TIME MARTINGALES
REYNOLDS TRANSPORT THEOREM
CONSERVATION OF DISSOLVED CONSTITUENT MASS

BROWNIAN MOTION
BROWNIAN MOTION
MARKOV PROPERTY
THE BROWNIAN SAMPLE PATHS

STOCHASTIC INTEGRATION
CONSTRUCTION OF THE STOCHASTIC INTEGRAL
THE CHANGE-OF-VARIABLE FORMULA
GENERALIZED ITO RULE FOR BROWNIAN MOTION

STOCHASTIC DIFFERENTIAL EQUATIONS (IF TIME PERMITTED)
STRONG SOLUTIONS
WEAK SOLUTIONS
APPROXIMATION METHODS FOR UNCERTAINTY ANALYSIS
FIRS-ORDER VARIANCE ESTIMATION METHOD
ROSENBLUETH;S PROBABILISTIC POINT ESTIMATE METHOD
HARR’S PROBABILISTIC POINT ESTIMATE METHOD
LI’S PROBABILISTIC POINT ESTIMATE METHOD 

課程目標
 THE OVERALL OBJECTIVE OF THIS COURSE IS TO FAMILIARIZE STUDENTS WITH BASIC CONCEPTS OF MATHEMATICAL MODELING UNDER UNCERTAINTY. STUDENTS ARE EXPECTED TO GAIN A BASIC UNDERSTANDING OF STOCHASTIC PROCESSES, UNCERTAINTY ANALYSIS AND FUNDAMENTAL STOCHASTIC CALCULUS USEFUL FOR STOCHASTIC MODELING. THIS COURSE WILL PROVIDE STUDENTS WITH FUNDAMENTAL KNOWLEDGE AND QUANTITATIVE APPROACHES NECESSARY FOR MODELING NATURAL PROCESSES UNDER UNCERTAINTY. THIS COURSE WILL BE TAUGHT IN ENGLISH. 
課程要求
 先修課程： 統計學或工程統計， 微積分或工程數學（一），或授課教師同意 
預期每週課後學習時數
  
Office Hours
 另約時間 
指定閱讀
  
參考書目
  
評量方式
(僅供參考)
    
課程進度
週次
日期
單元主題
Week 1
 9/16  Introduction 
Week 2
 9/23  Hot Topics and Challenges 
Week 3
 9/30  Sensors for Perception 
Week 4
 10/07  Range Sensors and Processing 
Week 5
 10/14  Scan Matching and Registration 
Week 6
 10/21  Midterm Exam I 
Week 7
 10/28  Cameras & Vision 
Week 8
 11/04  Uncertainty  
Week 9
 11/11  Localization 
Week 10
 11/18  Simultaneous Localization and Mapping (SLAM) 
Week 11
 11/25  Tracking 
Week 12
 12/02  Midterm Exam II 
Week 13
 12/09  Planning and Obstacle Avoidance 
Week 14
 12/16  Robot Learning & What To Do With 100 Million GPS Points http://research.microsoft.com/en-us/um/people/jckrumm/Presentations%202010/AutomotiveUI%20keynote.pptx 
Week 15
 12/23  Robot Learning 
Week 16
 12/30  Reinforcement Learning http://rlai.cs.ualberta.ca/RLAI/RLAIcourse/RLAIcourse.html 
Week 17
 1/06  Markov Decision Processes: Tutorial Slides by Andrew Moore http://www.autonlab.org/tutorials/mdp09.pdf 
Week 18
 1/13  Final Exam