METU
Middle East Technical University
Ankara, Turkey
 CENG 585
Fundamentals of Autonomous Robotics
Fall 2006-2007
 CENG
Department of Computer Engineering
Information
 Lectures
 Policies

Information
  • Instructor: Asst.Prof.Dr. Erol Sahin
  • Office hours:  TBA (to be announced)
  • Teaching Assistant: None.
  • Textbook: An Introduction to AI Robotics by Robin Murphy.  I will use this book only as a framework for the course. Other books and many articles will be used to supplement the book. The book is ordered by the METU Bookstore. Please keep me informed of its availability.
  • Course web page: http://kovan.ceng.metu.edu.tr/~erol/Courses/CENG585/
  • Time: Tuesdays 9:40-12:30
  • Location: A-101, Dept. of Computer Eng.
  • Communication:
    • If you have a specific question you can  send an e-mail to me but make sure that the subject line starts with CENG585 [capital letters, and no spaces] to get faster reply. In any case, questions that are general should be posted to the newsgroup.
 Announcements
  • Lecture notes for Week 8, 9, 10 and 11 are now available below.
  • Regarding paper presentations: If you have any paper that you wish to present, send it to me, and I'll decide.. If not, I'll give you a suggested paper list, from which you can choose.
  • Help for writing project reports in LatEX.

Lectures

What is autonomous robotics?
History of autonomous robotics

Sep 26

The image “http://www.frc.ri.cmu.edu/~hpm/project.archive/robot.papers/2000/revo.slides/1950.jpg� cannot be displayed, because it contains errors.
  • Topics
    • Overview and objectives
    • Industrial robotics
    • Tele-operated robotics
    • Autonomous robotics
    • Why Artificial Intelligence?
    • Braitenberg's vehicles
    • Walter Grey Walter's tortoises
  • Related readings:
    • Braitenberg, Valentino (1984) Vehicles: Experiments in Synthetic Psychology, The MIT Press, Cambridge, MA. Chapters 1-4.
    • Creatures, chapter 1 from R. Brooks' unpublished book.
  • Slides
  • Links


Challenges in autonomous robotics.
Technology of robots

  Oct 3
The image “http://www.boskowan.com/www/jirka/asimo/honda-asimowalk.jpg� cannot be displayed, because it contains errors.

Autonomous Robotics Control Architecture Paradigms

Oct 10
  • Topics
    • Overview of three paradigms
      • Hierarchical paradigm
      • Reactive paradigm
      • Hybrid deliberative/reactive paradigm
    • Hierarchical architectures
      • STRIPS
    • Biological motivations for reactive paradigm
      • Ethology
  • Related readings:
    • R.E.Fikes and N.J.Nilsson, STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving, Artificial Intelligence, vol. 2 (1971), pp. 189--208. a.k.a STRIPS paper.
  • Assignments due:
  • Lecture Notes:
  • Links
Robot Control Paradigms
and
Subsumption Architecture

Oct 17
The image “http://www.astrosurf.org/lombry/Documents/robot-genghis-ai-brooks.jpg� cannot be displayed, because it contains errors.
  • Topics
    • Reactive Paradigm
    • Subsumption architecture
      • Case study 1: Layered control of a wheeled mobile robot
      • Case study 2: Design of the Genghis (a hexapod) control system
    • Philosophical discussions
  • Related readings:
    • Ch 2 [A Creature Renaissence] from R. Brooks
    • A Robust Layered Control System for a Mobile Robot (1986). R. Brooks. IEEE Journal of Robotics and Automation, pp 14-23. Also published as Chapter 1 of the book Cambrian Intelligence. [Available as a technical report here].
    • A Robot that walks: Emergent behaviors from a carefully evolved network (1989). R. Brooks. Neural Computation, pp 253-262. Also published as Chapter 2 of the book Cambrian Intelligence. [Available as a technical report here].
    • Intelligence without representation (1991), R.A. Brooks, Artificial Intelligence Journal 47, pp 139-160. Also published as Chapter 5 of the book Cambrian Intelligence.
  • Assignments due:
    • Just read the STRIPS paper. No other assignments.
  • Lecture Notes:
No class due to Seker Bayrami
Oct 23
Schema Theory and Motor Schemas
Oct 30
  • Topics [Guest Lecturer: Emre Ugur]
    • Schema Theory
    • Motor schemas
    • Robot schemas
    • Arbitration of behaviors
    • Reactive vs Behavior-based control
  • Related readings
    • A Formal Model of Computation for Sensory-Based Robotics, D. Lyons and M. Arbib
      IEEE Transactions on Robotics and Automation. 1989, volume 5, 3, pages 280-293. [Available at the photocopy room]
    • Motor Schema-Based Mobile Robot Navigation, Ronald Arkin. International Journal of Robotics Research. 1989, volume 8, 4, pages 92--112. [Available at the photocopy room]
  • Assignments:
  • Lecture Notes:
  • Links related:
Hybrid Architectures


Nov 7
  • Topics [Guest Lecturers: Emre Ugur, Maya Cakmak, Mehmet R. Dogar]
    • Hybrid architectures
    • Three level architectures
      • AuRO
      • RAPs
      • Planner-reactor
  • Related readings:
  • Assignments:
  • Lecture Notes:
  • Links related:
Robot Programming

Nov 14
  • Topics [Guest Lecturer: Dr. Izzet Pembeci]
    • A review of Robot Programming Languages
    • FROG: A functional robot programming language
  • Related readings:
  • Assignments:
  • Lecture Notes:
  • Links related:
No Class
Nov 21
Mobile robot navigation -1

Nov 28
  • Topics
    • Three main problems of robot navigation
    • RelativePositioning
      • dead-reackoning
    • Absolute positioning
    • Metric and topological  maps
    • C-space representation
    • Meadow maps and Generalized Voronoi Diagrams
    • A and A* path finding algorithm
  • Readings:
    • Part III [Navigation] of the textbook.
    • Ch 9 [Topological path planning] of the textbook.
    • Ch 10 [Metric path planning] of the textbook.
  • Assignments:
  • Lecture Notes:
  • Links related:

Mobile robot navigation -2

Dec 5
  • Topics
    • Occupancy grids
    • ARIEL architecture: Exploration and map building
    • SLAM (Simultaneous Localization and Mapping)
      • Kalman filtering
  • Readings:
    • Ch 11 [Localization and map making] of the textbook.
    • Simultaneous map building and localization for an autonomous mobile robot. Leonard, J.J.; Durrant-Whyte, H.F.; Intelligent Robots and Systems '91. 'Intelligence for Mechanical Systems, Proceedings IROS '91. IEEE/RSJ International Workshop on , 3-5 Nov. 1991 Page(s): 1442-1447 vol.3. [Paper available here]
  • Assignments:
  • Lecture Notes:
  • Links related:


Design and Programming of Autonomous Legged Robots for Dynamics Locomotion

Dec 12
  • Topics [Guest Lecturer: Asst.Prof.Dr. Uluc Saranli]

      • RHex: The Robotic Hexapod
      • Linear Logic for programming robots with dynamics control requirements
  • Assignments:
  • Lecture Notes:

Evolutionary Robotics


  Dec 19

  • Topics
    • Evolutionary robotics
    • Karl Sim's evolved creatures
  • Readings:
    • Ch 1 [The role of self-organization for the synthesis and the understanding of behavioral systems] Evolutionary Robotics; The Biology, Intelligence, and Technology of Self-Organizing Machines by Stefano Nolfi and Dario Floreano, MIT Press/Bradford Books. 
    • Ch 2 [Evolutionary and neural techniques] Evolutionary Robotics; The Biology, Intelligence, and Technology of Self-Organizing Machines by Stefano Nolfi and Dario Floreano, MIT Press/Bradford Books. 
    • Ch 3 [How to evolve robots] Evolutionary Robotics; The Biology, Intelligence, and Technology of Self-Organizing Machines by Stefano Nolfi and Dario Floreano, MIT Press/Bradford Books. 
    • Pollack, Jordan. B., Lipson, Hod, Hornby, Gregory S. and Funes, Pablo (2001). Three Generations of Automatically Designed Robots.  Artificial Life, 7:3. [Paper available here]
  • Assignments:
  • Lecture Notes:
    • Week 10
      • Evolutionary Robotics Tutorial: pdf | ppt
      • Karl Sims' work on evolving virtual creatures: pdf | ppt
  • Links related:

Research snapshots:
Cognitive robotics
&
Collective robotics 

  Dec 26
  • Topics
    • Cognitive Robotics
    • Swarm robotics
    • Alper Erdener's presentation
    • Iskender Yalcin's presentation
  • Readings:
    • Cooperative Mobile Robotics: Antecedents and Directions by Y. Uny Cao, Autonomous Robots 4(1):7 - 27.  [Paper available here]
    • Dudek G., Jenkin M. R. M., Milios E., and Wilkes D., A Taxonomy for Multi-Agent Robotics. Autonomous Robots, 1996, Vol. 3, pp. 375-397. [Paper available here]
    • The RoboCup Challenge, Robotics and Autonomous Systems, Volume 29, Issue 1, 31 October 1999, Pages 3-12 Minoru Asada and Hiroaki Kitano. [Paper available here]
  • Assignments:
  • Lecture Notes:
  • Links related:
Student presentations
[Extra Class]
Student presentations

Jan 10
  • Topics
    • Fatih Gokce's presentation: Real-Time Obstacle Avoidance for Fast Mobile Robots
    • Hande Celikkanat's presentation:
      • Cognitive Robotics
    • Umut Erogul's presentation:
    • Sarper Alkan's presentation: A mobile robot employing insect strategies for navigation
    • Deniz Eroglu's presentation;
      • Humanoid Robot HRP-2
      • Cognitive developmental robotics as a new paradigm for the design of humanoid robots
Student presentations
[Extra Class]
Student presentations

Jan 11
  • Topics
    • Cihan Ozturk's presentation: Inertial Navigation and Visual Line Following
    • Akin Avci's presentation: Adjusting Step Length for Rough Terrain Locomotion
    • Atil Iscen's presentation: Robocup Rescue
    • Ufuk Dogan: From Local Actions To Global Tasks: Stigmergy
      and Collective Robotics
    • Onur Dogan: "Evolving Robots Able To Integrate Sensory-Motor Information Over
      Time"
Robot vision
  • Topics
    • CMU cart
  • Readings:
    • DeSouza G.N., Kak A.C., "Vision for Mobile Robot Navigation", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 2, pp. , Feb. 2002. [
  • Assignments:
  • Lecture Notes:
  • Links related:
    • Biorobotic Vision Laboratory: http://cvs.anu.edu.au/bioroboticvision/brv.html

  • Topics
    • Sensory-motor coordination
  • Readings:
    • R. Pfeifer and C. Scheier. Sensory-motor coordination: The metaphor and beyond. Robotics and Autonomous Systems (Special Issue), 20:157--178, 1997. [
  • Assignments:
  • Lecture Notes:
  • Links related:

Policies
  • Registration: The size of the class is limited and therefore I will try to make the class available to the most interested students.
  • Objective: Autonomous robots have become a  test-bed for artificial intelligence. Developing a full- or semi-autonomous robot that is physically embodied in the world is subject to many restrictions, such as local sensing, unstructured environment and real-time execution/adaptation. This course aims to 1)  cover the evolution of artificial intelligence approaches to autonomous robotics  2) introduce the fundamental problems/requirements/contraints of autonomous robotics research 3) present seminal works in the field, and 4) make the students to study some of the problems on physical robots or robot simulators.
  • Prerequisites: Consent of the instructor is essential.  Calculus I and II (or equivalent level of math), Introduction to Programming (Ceng 210-220-230) and a Data Structures course. Experience in mechanics or electronics is not required.
  • Grading:
    • Project (60%)
    • Paper presentation (10%)
      • If you have done a specific project, then you will present your work.
      • Otherwise, you will be asked to review a set of papers and make a 15 minute presentation in class.
    • Homeworks (30%)
      • All lectures have reading assignments, consisting of some chapters from the texbook as well as extra reading material (mostly papers).  Related to these readings, you will be given a short list of questions to be answered in a prior lecture. The homeworks are expected to be submitted by the beginning of each class. Late submissions will not accepted. If you are not able to read the readings, then do not attempt to cheat by copying it from another one's homework.

  • Late assignments

    • All assignments are due the start of a class. Assignments submitted after 15 minutes  of a class are considered late.
    • Homeworks submitted late will not be accepted!
    • Reports submitted late are eligible for a maximum of 80% credit.  Projects submitted after 2 weeks of their due date are worth at most 60% credit. Any project not submitted within two weeks of its due date receive no credit.
    • Paper presentations have to be made at the scheduled time.  Re-scheduling [at least one week in advance] without legal (e.g. health) excuses will cause the loss of 50% of the credit. 
      • Presentation guidelines:  You are given one or two papers to be presented. Your task is to prepare a 20 minute presentation about the paper[s]. You should fully understand the papers, and present it. The style of presentation is very important. Your slides should contain the main points that you will be talking [no full sentences!]. Try to make your slides "light" but informative. Resort to images/graphics wherever possible. Also rehearse your talk couple of times before your presentation. During and after the presentation you will be grilled by questions, and your performance in replying is also very important.