Social Robotics Lab, University of Freiburg

// 1. Include Header

Faculty of Engineering > Department of Computer Science >

Winter Term 14/15

Human-Oriented Robotics

The course will introduce basic and advanced concepts and methods in robotics, machine learning, artificial intelligence and human-robot interaction. In particular, we will consider robotics with the "human in the loop" which is concerned with key technologies that enable robots to better live, work and interact with humans. This is a growing research field with many new and exciting applications such as companion robots, health-care robots, autonomous cars, human-robot cooperation in manufacturing, search and rescue etc. In addition to their theoretical treatment, the methods will be exemplified with Matlab programming exercises. The course outline is as follows:

Introduction
Basics

Matlab/Octave introduction
Probability refresher, common distributions
Probabilistic reasoning, Bayes networks, Markov chains

Perception of Humans

Supervised learning: naive Bayes, logistic regression, SVM, AdaBoost, k-NN, cross-validation
Unsupervised learning: hierarchical clustering, k-means, GMM and EM
Temporal Reasoning: Hidden Markov Models, LDS and Kalman filtering, error propagation
Tracking and data association: NN, GNN, PDAF, JPDAF, MHT

Planning among Humans

Robot motion planning: combinatorial techniques, PRM, RRT, potential fields, A*, Theta*, obstacle avoidance
From plans to policies: Markov Decision Processes (MDP)

Interaction with Humans

Introduction to Human-Robot Interaction

We assume that students have a laptop with Matlab installed (download and install instructions can be found here). Octave, the open-source alternative to Matlab, can also be used (download for free from www.octave.org) but some exercises will require Matlab-only functionalities.

People

Lecturer: Prof. Kai Arras
Lab instructors: Timm Linder, Luigi Palmieri, Billy Okal

Organization

Lectures: Tuesday 10h-12h, Building 101, Room SR 01 018
Exercises: Thursday 12h-14h, Building 101, Room SR 01 018
Exams: Tuesday, March 3, 2015 and Friday, March 27, 2015.
Building 074, Office 015. Enter the building by the parking lot, not the Uni Radio.
Language: English
Recordings: I want you to participate :-) so no recordings

Requirements

No formal requirements.

Exercises

Solving and submitting the exercise sheets does influence the exam grade.
There are no exam admission requirements.
In general, assignments will be published on Tuesday and have to be submitted the following Tuesday before class.
Submit programming exercises via email to the address indicated on the respective sheet.

Exercise Sheets

Exercise 1, Matlab/Octave basics: sheet, data
Exercise 2, Introduction to probability: sheet, data
Exercise 3, Basics of probabilistic reasoning: sheet
Exercise 4, Naive Bayes classifier: sheet, data
Exercise 5, Support vector machines: sheet, data
Exercise 6, k-NN, cross-validation: sheet, data
Exercise 7, k-Means clustering: sheet, data
Exercise 8, Hidden Markov model: sheet, data
Exercise 9, Kalman filter: sheet, data
Exercise 10, Tracking and data association: sheet, data
Exercise 11, Rapidly-exploring random trees: sheet, data
All solutions

Slides and Additional Material

Nr.	Title	Additional Material
1.	Introduction (20 slides)
2.	Matlab/Octave Tutorial (121 slides)	Matlab online documentation Octave user manual (pdf) Install Matlab from here (University of Freiburg only) SRL librobotics library
3.	Probability Refresher (54 slides)	Pattern Recognition and Machine Learning by C.M. Bischop, Springer, 2007 Probabilistic graphical models: principles and techniques by D. Koller, N. Friedman Probability, Random Variables and Stochastic Processes by A. Papoulis, S.U. Pillai Computer vision: models, learning and inference by S.J.D. Prince
4.	Basics of Probabilistic Reasoning (38 slides)
5.	Supervised Learning 1/3: Basics, Naive Bayes, logistic regression (48 slides)	Artificial Intelligence: A Modern Approach by S. Russell, P. Norvig Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression by T. M. Mitchel, in: Machine Learning, Chapter 1, 2010. Estimating continuous distributions in Bayesian classifiers by G. John, P. Langley, UAI 1995.
6.	Supervised Learning 2/3: Support Vector Machines (67 slides)	SVM Applet by A. Karpathy. Very instructive! Part V: Support Vector Machines by A. Ng, Lecture Notes CS229 Machine Learning, Stanford University, 2012 Support Vector Machines Explained by T. Fletcher, Tutorial Paper, 2009
7.	Supervised Learning 3/3: AdaBoost, k-NN, cross-validation (82 slides)	K-NN and Potential Energy Applet by E.M. Mirkes. Very instructive! Introduction to Machine Learning by E. Alpaydin, The MIT Press, 2009 Debugging Learning Algorithms by A. Ng, A lecture on getting machine learning algorithms to work in practice, 2007
8.	Unsupervised Learning: AHC, k-means, GMMs and EM (70 slides)	K-means and K-medoids Applet by E.M. Mirkes. Very instructive! EM for Mixture Models Applet by I. Dinov. Very instructive! Introduction to Data Mining by P.-N. Tan, M. Steinbach, V. Kumar, Addison-Wesley, 2005 Pattern Recognition by S. Theodoridis, K. Koutroumbas, 4th ed., Elsevier, 2009 Data clustering: 50 years beyond K-means by A.K. Jain, Pat. Rec. Letters, 31(8), 2010
9.	Temporal Reasoning 1/3: Basics, HMM (77 slides)	A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition by L.R. Rabiner, Proc. of the IEEE, 77(2), 1989 mathematicalmonk YouTube channel, Machine learning lectures 14.4-14.12 on HMM
10.	Temporal Reasoning 2/3: LDS, Kalman filter (101 slides)	Estimation with Applications to Tracking and Navigation by Y. Bar-Shalom, X. Rong Li, T. Kirubarajan, Wiley, 2001 Probabilistic Robotics by S. Thrun, W. Burgard, D. Fox, MIT Press, 2005
11.	Temporal Reasoning 3/3: Tracking and Data Association (83 slides)	Tracking and Data Fusion: A Handbook of Algorithms by Y. Bar-Shalom, P.K. Willett, X. Tian, YBS Publishing, 2011 Beyond the Kalman Filter: Particle Filters for Tracking Applications by B. Ristic, S. Arulampalam, N. Gordon, Artech House, 2004
12.	Robot Motion Planning: Basics, combinatorial and sampling-based methods (67 slides)	Robot Motion Planning by J.C. Latombe, Kluwer Academic Publishers, 1991 Planning Algorithms by S. LaValle, Cambridge University Press, 2006 Principles of Robot Motion: Theory, Algorithms, and Implementations by H. Choset, K.M. Lynch, S. Hutchinson, G. Kantor, W. Burgard, L.E. Kavraki, S. Thrun, MIT Press, 2005 Chapters 5 and 6 in Handbook of Robotics ed. by B. Siciliano, O. Khatib, Springer, 2008 Configuration Space Applet by K. Goldberg, E. Lee, J. Wiegley. Very instructive!