Class information
Room: Science Center 252
Time: Tuesday, Thursday 2:40–3:55pm
Professor: Lisa Meeden
Office: Science Center 243
Phone: 328-8565
Office hours:Wednesday 2-4pm or by appointment
Introduction
This seminar will focus on the special topic of developmental
robotics, a newly emerging paradigm of research. The goal of this
research is to create intelligent robots by allowing them to go
through a developmental process, rather than being directly programmed
to solve a particular task. By endowing a robot with an appropriate
initial control architecture and adaptive mechanisms, it can learn
through continual interactions with the world, developing
self-organized knowledge about itself and its environment. We will be
studying the following sorts of questions: What should be innate in
the robot? What adaptive mechanisms are needed? What motivates the
robot to act?
Goals for the course
-
Analyze and critically discuss research papers on developmental
robotics both in writing and in class.
-
Understand the fundamental questions in the field of developmental
robotics and be able to analyze different solutions to these questions.
-
Formulate and evaluate a hypothesis about developmental robotics by
proposing, implementing and testing a project.
-
Relate your project to prior research via a review of related literature.
-
Orally present a clear and accessible summary of your project.
-
Write a coherent, complete paper describing and evaluating your project.
You can see examples of past projects at CS81 Spring 2006.
Grading
-
Class Participation and Paper Summaries: 25%
Bring a typed summary of the designated paper to class. You will turn
this in at the end of class. The summary must include:
- A 1-2 paragramph summary of the paper, describing its main points,
and why you think this paper is important.
- A list of questions that we can discuss during the seminar. These
may include questions of clarification, but should largely be made up
of more interesting questions. These might include: how this paper
fits into the field as a whole or how could the experiments be
improved or expanded.
At the end of class you will also complete a self-evalutation of your
particiaption in the seminar discussion.
Your participation will be evaluated with this
form.
- Midterm Project: 25%
There will be a mid-semester
project assigned on February 14 and due on March 5. The goal of this
project is to give you a preview, on a smaller scale, of what will be
expected on the final project.
- Final Project: 50%
You will be asked to design a project
related to developmental robotics. These projects may be carried out
alone or in groups of two or three students.
-
Proposal 5%
Due in class on Tuesday, March 25.
-
Checkpoint demonstration 5%
Shown in class on Tuesday, April 8.
-
Presentation 10%
Done in class during the last two weeks of the semester.
-
Paper 30%
Due in my office by 4pm, Monday, May 12.
Schedule
| WEEK |
DAY |
ANNOUNCEMENTS |
READING |
| 1 |
Jan 22 |
|
Introduction to developmental robotics Meeden and Blank |
| Jan 24 |
|
Developmental Robotics: A survey Lungarella, Metta, Pfeifer, and Sandini |
| 2 |
Jan 29 |
|
Sensory flow segmentation using a RAVQ Linaker and Nilasson
A growing neural gas network learns topologies Fritzke |
| Jan 31 |
Drop/Add ends (Feb 01) |
No class |
| 3 |
Feb 05 |
|
Introduction to Khepera, Aibo, and Pioneer robots |
| Feb 07 |
|
Learning concepts by interaction Cohen
Continuous categories for a mobile robot Rosenstein and Cohen
Identifying qualitatively different experiences: Experiments with a mobile robot Oates, Schmill, and Cohen |
| 4 |
Feb 12 |
|
Developing navagation behavior through self-organizing distinctive state abstraction Provost, Kuipers, Mikkulainen |
| Feb 14 |
Midterm project |
Map learning with uninterpreted sensors and effectors Pierce and Kuipers |
| 5 |
Feb 19 |
|
Intrinsic motivation systems for autnomous mental development Oudeyer, Kaplan, Hafner |
| Feb 21 |
|
An emergent framework for self-motivation in developmental robotics Blank, Marshall and Meeden
Intrinsicaly motivated reinforcement learning: A promising framework for developmental robot learning Stout, Konidaris and Barto |
| 6 |
Feb 26 |
|
Midterm project checkpoint demonstration |
| Feb 28 |
|
Is imitation learning the route to humanoid robots? Schaal |
| 7 |
Mar 04 |
Midterm project due 4pm (Mar 05) |
Imitation of facial and manual gestures by human neonates Meltzoff and Moore
Imitation of other minds: The 'Like Me' hypothesis Meltzoff |
| Mar 06 |
|
No class |
| |
Mar 11 |
Spring Break |
Mar 13 |
| 8 |
Mar 18 |
|
Self-organizing distinctive state abstraction using options Provost, Kuipers, and Miikkulainen |
| Mar 20 |
|
The robot in the crib: A developmental analysis of imitation skills in infants and robots Demiris and Meltzoff
From exploration to imitation: Using learnt internal nodels to imitate others Dearden and Demiris |
| 9 |
Mar 25 |
Final project |
Division blocks and open-ended evolution of development, form, and behavior Spector, Klein, and Feinstein |
| Mar 27 |
Last day to declare CR/NC or withdraw (Mar 28) |
A developmental model for the evolution of complete autonomous agents Dellaert and Beer |
| 10 |
Apr 01 |
|
Emergence of communication in teams of embodied and situated agents Marocco and Nolfi |
| Apr 03 |
|
Demonstration by Doug Blank |
| 11 |
Apr 08 |
|
Final project checkpoint demonstration |
| Apr 10 |
|
Evolution and learning Nolfi and Floreano
|
| 12 |
Apr 15 |
|
Competitive coevolution through evolutionary complexification Stanley and Miikkulainen |
| Apr 17 |
|
Hierarchical evolution of neural networks Moriarty and Miikkulainen |
| 13 |
Apr 22 |
|
Presentations
1. Michael and Eric
2. David |
| Apr 24 |
|
Presentations
1. Megan and Chris
2. Jeff |
| 14 |
Apr 29 |
|
Presentations
1. George and Kit
2. Bryce and Allison |
| May 01 |
Final project paper due 4pm (May 12) |
Presenations
1. Mary and Marie |
Final Projects