CS 395T: Intelligent Robotics
- Spring 2003. TTh, 3:30 - 5:00 pm
- TAY 3.144
- Unique #52084.
- Professor Benjamin Kuipers
- Office hours: TBD
In this seminar, we will study the problem of how an agent can learn
to perceive its world well enough to act in it and make reliable
plans. Studying this problem in the context of physical robots forces
us to confront the continuous nature of sensory input, of action, and
of the environment in which the agent exists. Our goal is to
determine how the agent can discover useful abstractions from
continuous sensorimotor experience, to build symbolic knowledge
representations describing its world.
Closely related to this is the problem of a long-lived and complex
robot adapting to the inevitable changes in its sensorimotor system.
Some sensors will fail. Others will drift out of calibration.
It may be possible for certain sensors to learn to improve their
sensing ability over time. And new sensors, and even entirely
new sensory modes, could be plugged in to the robot. How does it
adapt to these changes, by learning from its own experience?
This problem is of practical importance, because the robots of the
future will have increasingly rich sensory systems. It will be
necessary for them to learn from their own experience how their
sensors respond to the world and how the world responds to the actions
they take. The meanings of symbols in their knowledge representation
are then "grounded" in the nature of their sensorimotor interaction
with the environment. In addition to its practical importance, this
problem is central to the philosophical problem of whether artificial
intelligence is possible at all (Searle, Harnad).
Experiments and assignments will be done on simulated and physical
robots. One of our physical robots is a prototype of an intelligent
This is a research seminar, intended first to bring you to the state
of the art, and then to help you do a project and paper of publishable
quality. There will be a significant amount of reading of research
papers that will be handed out.
There will be several mathematical and programming assignments, a term
project and a presentation.
Each class member will select a topic and present the material to the
class. Each topic will have an associated reading that the entire
class will read, but the presenter is responsible for finding and
reading additional material, becoming an expert in the area, creating
an illuminating example to present, and leading a discussion.
Plan to give a 25 minute presentation, followed by questions and
discussion of the value and importance of the material presented.
- What is the problem? Why is it important? Why should the reader care?
- What assumptions are being made?
- How does this method work? (Provide an intuition that will guide
the hearer as they read the technical details.)
- What are the strengths and limitations of this approach?
- How can you evaluate the benefits?
- What are open problems in this area?
- How does this help us?
Where is the gold?
Pick a presentation topic that works well with your term project
topic. (We may spend multiple sessions on some of these.)
Each class member will do a term project. You can apply a method we
are learning about to a robot learning problem. Or you can extend an
existing method or develop a new method to solve a problem. Ideally,
your term project will extend the state of the art, and will be
suitable for submission to AAAI or ICRA or some other major conference.
You are encouraged to select a topic that fits well with your other
Topics for Presentations and Projects
I will present various aspects of the research currently going on
in our group. Project and presentation topics will deal with other
approaches to the same problem, and may involve integrating their
best properties into our framework.
Representing and learning control laws
- Motion Description Language (MDL and MDLe), Roger Brockett, et al.
- Probabilistic Roadmaps (PRM), Jean-Claude Latombe, et al.
- Hidden Markov Models (HMMs) and Partially Observable Markov
Decision Processes (POMDPs), Leslie Kaelbling, et al.
- Behavioral cloning (learning skills by observing experts),
Dorian Suc, et al.
Learning sensorimotor features
- The schema mechanism, Gary Drescher, et al.
- Learning to recognize places from sensory images.
- Hand-eye coordination by learning Jacobians.
- Sensor calibration and fault detection, Alice Agogino,
Volker Graefe, et al.
Recent steps in robot mapping
- Topological mapping, Emilio Remolina, Howie Choset, et al.
- Simultaneous Localization and Mapping (SLAM), John Leonard,
Sebastian Thrun, et al.
- 3D mapping: metrical models, Thrun ,et al; topological models.
Cognitive maps in rats and humans
- Neuroscience studies of brain structures: O'Keefe and Nadel,
Bruce McNaughton, David Redish, David Touretzky, et al.
- Cognitive studies of way-finding, Hans-Peter Mallot,
Brian Stankiewicz, et al.
- Comparative animal studies, Trullier, et al.
This list will be fleshed out with more references, and very likely
more topics, by the time the class starts.
These are some useful books that you should have in your professional
library, and that are related to this course. I will assume that
you have immediate access to material in these books.
If you do not already have a background in Artificial Intelligence,
you should invest in the following excellent textbook. It's another
valuable addition to your library, and is undoubtedly available used.
- Duda, Hart and Stork. 2001. Pattern Classification, Second Edition.
NY: John Wiley and Sons.
(This book is a useful reference for your library.)
- Tom Mitchell. 1997. Machine Learning. Boston: McGraw-Hill.
(This book is a useful reference, and is the required text for
Ray Mooney's Machine Learning course.)
You will also need to do assignments in either MATLAB or LabVIEW.
Make sure you have any documentation you need.
- Stuart Russell and Peter Norvig. 1995. Artificial
Intelligence: A Modern Approach. Prentice-Hall.
The following monograph is, I believe, an important early exploration
of some of the problems we want to solve. It contains some significant
pieces of the puzzle, but we don't yet know how to re-use them.
We will definitely discuss it. Buy it if you want to do research
in this area.
- Gary L. Drescher. 1991. Made-Up Minds: A Constructivist Approach
to Artificial Intelligence.
Cambridge, MA: MIT Press.
Resources (check for updates)
You may find interesting resources in the syllabus for
CS 395T: Robot Learning, which was taught in