A VISION-BASED PERCEPTUAL LEARNING SYSTEM FOR AUTONOMOUS MOBILE ROBOT By

ii ACKNOWLEDGEMENTS I would like to take this opportunity to thank Dr. Mitch Wilkes, the chairman of my Ph.D committee, for being so supportive of my academic goals and for being so kind to provide me with the protected academic time and financial aid to pursue these goals. As my advisor and mentor, he has shown me what a good professor should be. I am also grateful to all of those whom I have had the pleasure to know during my study at Vanderbilt, particularly, the Electrical Engineering department, which supported me financially to fulfill my course work, Dr. James A Cadzow and Dr. Francis Wells, who helped me enter the Ph.D program, Dr. Kawamura, without his strict requirements on my research proposals I could not be clear about what I was supposed to do for my Ph.D, Dr. David Noelle, without his kind suggestions and efforts about my proposed experiments I could not be able to finish my study so soon, Dr. Douglas Hardin and Dr. Nilanjan Sarkar, who are so nice to be willing to serve on my committee, Dr. Bharati Mehrotra, who is so kind to be willing to share with me her experiences as a scientific researcher, Flo Fottrell and her husband, for always being there to cheer me up and to teach me how to make appetizers,hammadi for their friendships and technical supports. Without all these helps, this work would not have been possible. Finally, I would like to thank my parents, my brother and my sister-in-law, and my lovely nephew for their unconditional love, financial support and guidance which are with me in whatever I pursue. iii ABSTRACT Autonomous robots are intelligent machines capable of performing tasks in the real world without explicit human control for extended periods of time. A high degree of autonomy is particularly desirable in fields where robots can replace human workers, such as state-of-the-practice video surveillance system and space exploration. However, not having human's sophisticated sensing and control system, two broad open problems in autonomous robot systems are the perceptual discrepancy problem, that is, there is no guarantee that the robot sensing system can recognize or detect objects defined by a human designer, and the autonomous control problem, that is, how the robots can operate in unstructured environments without continuous human guidance. As a result, autonomous robot systems should have their own ways to acquire percepts and control by …