CS533 Situated Computing: Foundations in Visual Theory, Brain, and Robotics
(new Course)

Proposed by Christopher Jaynes

Credits: 3


Course Description:

 This course covers the fundamental concepts involved in understanding and
engineering a closed-loop, sensing, reasoning, and actuating agent.  
Biological models of vision and actuation will be discussed and related
to modern artificial counterparts.  Landmark readings from computer science,
psychology, ethology, and biology will provide students with a theoretical 
framework for the course.  

The course is broken into three major topic areas; Vision, Brain, and Robotics.
The vision component of the course will introduce students to the issues
in Computer and Biological vision, including color perception, theories of
object recognition and permanence, and scene understanding.  Using the 
ideas developed in the vision component, we will introduce 
models of belief representation and modification, both biological and
machine architectures for percept processing and reasoning, machine 
learning for vision, neural networks, path planning, and intelligent 
localization based on visual cues.  Finally, the course will introduce 
students to robotics, including forward and inverse kinematics, intelligent 
grasping, and the integration of perception and action. 


Prerequisites:	CS560 Artificial Intelligence

Required Skills:

Students should be familiar with topics in artificial intelligence problem 
solving methods, including search, min-max game theory, 
and basic knowledge representation schemes.  Students should show
the mathematical maturity expected of first-year graduate students.


Learning Outcomes:

Students will learn a broad base of concepts dealing with the design and 
implementation of a situated agent capable of sensing and acting intelligently
on its world.  The core concepts learned will be computer vision, models of
intelligent computation in both machines and biological systems, and robotics.
Students will be asked to implement a specific agent in the "Bugs World"
simulator, based on Braitenburg vehicles.  Student designed agents will use
vision, reasoning, and control to compete for resources within the simulator, 
while avoiding predators.

A variety of readings in conjunction with lectures will provide students will 
the tools necessary to implement and understand the theoretical foundations 
in modeling situated agents. Students will understand the issues in a variety 
of topics in artificial intelligence including, computer vision, learning, 
neural networks, and robotics.  Concepts acquired from will serve as a 
foundation for the Computer Vision courses (CS635/CS636), 
Visualization (CS638), and other advanced topics involving intelligent search, 
sensation, and actuation.


Course Content:

 * Introduction
	Course Overview
	History:
		Cybernetics (readings in Weiner)
		Ethology    (readings in K. Lorenz)
		Epistemology of AI
 * Vision
	Human Visual System
	Vision/Conceptual Development (e.g. Piaget)
	Issues in Computer Vision
	Vision Geometry
	Stereo Vision
	Motion Understanding, Tracking

 * Reasoning, 
	Knowledge Representation
 	Neural Networks
	Learning
	Planning
	Genetic Algorithms
	Situated Architectures
		-Subsumption
		-Colossus
	Cooperative computation

 * Control/Robotics
	Active Vision/Control
	  Foveation
	Kalman Filtering
	Discrete Event Dynamic Systems
	Robotics: Forward/Inverse Kinematics
	Reactive Behavior

 * Applications


 * Simulation of Robotic Behavior: The Bugs World


Textbooks:

 - Active Robot Vision : Camera Heads, Model Based Navigation and Reactive 
   Control.   H. I. Christensen (ed.), World Scientific Pub Co; 1993.

 - Vision, Brain, and Cooperative Computation. Michael Arbib and Allen Hanson
   (eds).MIT Press, 1987.

 - The Artificial Life Route to Artificial Intelligence: Building Embodied,
  Situated Agents., Luc Steels and Rodney Brooks, Lawrence Erlbaum Assoc., 1995.