Chow Ying-ho. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2000. / Includes bibliographical references (leaves 78-83). / Abstracts in English and Chinese. / Chapter Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Objectives - Visual Navigation for Legged Robots --- p.1 / Chapter 1.2 --- Summary of Results --- p.3 / Chapter 1.3 --- Hardware Issues --- p.4 / Chapter 1.4 --- Contributions --- p.4 / Chapter 1.5 --- Organization of the Thesis --- p.4 / Chapter Chapter 2 --- Previous Work --- p.6 / Chapter 2.1 --- Vision Based Navigation --- p.6 / Chapter 2.1.1 --- Homography --- p.7 / Chapter 2.1.2 --- Ground Plane Obstacle Detection --- p.9 / Chapter 2.1.3 --- Regression --- p.12 / Chapter 2.2 --- Control Strategy --- p.13 / Chapter Chapter 3 --- System Overview --- p.16 / Chapter Chapter 4 --- Obstacle Detection by Fast Homography Estimation --- p.20 / Chapter 4.1 --- Ground Feature Extraction --- p.21 / Chapter 4.2 --- Ground Feature Correspondence --- p.21 / Chapter 4.3 --- Ground Homography Estimation --- p.24 / Chapter 4.3.1 --- Input point transformation --- p.24 / Chapter 4.3.2 --- Initial estimation --- p.26 / Chapter 4.3.3 --- Robust estimation --- p.27 / Chapter 4.4 --- Obstacle Detection --- p.29 / Chapter 4.5 --- Local Obstacle Map (LOM) on Ground --- p.33 / Chapter 4.5.1 --- Extraction from accumulative evidence --- p.34 / Chapter 4.5.2 --- Time-delay compensation --- p.34 / Chapter Chapter 5 --- Obstacle Avoidance by a Fuzzy Controller --- p.36 / Chapter 5.1 --- Gait Pattern --- p.38 / Chapter 5.2 --- Fuzzy Logic Controller --- p.42 / Chapter 5.2.1 --- Controller Inputs --- p.42 / Chapter 5.2.2 --- Controller Outputs --- p.43 / Chapter 5.2.3 --- Inference mechanism --- p.46 / Chapter Chapter 6 --- Implementation --- p.49 / Chapter 6.1 --- Hardware components --- p.49 / Chapter 6.1.1 --- VisionBug --- p.49 / Chapter 6.1.2 --- RF transmitter / receiver modules: --- p.52 / Chapter 6.2 --- Perception --- p.55 / Chapter 6.3 --- Image Calibration --- p.56 / Chapter 6.4 --- Motion Calibration: --- p.58 / Chapter 6.5 --- Software Programs --- p.66 / Chapter 6.5.1 --- Computational complexity --- p.68 / Chapter Chapter 7 --- Experimental Results --- p.69 / Chapter 7.1 --- Real Navigation Experiments --- p.70 / Chapter 7.2 --- Error Analysis of LOM --- p.73 / Chapter Chapter 8 --- Conclusion and future work --- p.76

"Consider two people having a face-to-face conversation. They sometimes listen, sometimes talk, and sometimes interrupt each other. They use facial expressions to signal that they are confused. They point at objects. They jump from topic to topic opportunistically. When another acquaintance walks by, they nod and say hello. All the while they have other concerns on their mind, such as not missing the meeting that starts in 10 minutes. Like many other humans behaviors, these are not easy to replicate in artificial agents. In this work we look into the design requirements of an embodied agent that can participate in such natural conversations in a mixed-initiative, multi-modal setting. Such an agent needs to understand participating in a conversation is not merely a matter of sending a message and then waiting to receive a response -- both partners are simultaneously active at all times. This agent should be able to deal with different, sometimes conflicting goals, and be always ready to address events that may interrupt the current topic of conversation. To address those requirements, we have created a modular architecture that includes distributed functional units that compete with each other to gain control over available resources. Each of these units, called a schema, has its own sense- think-act cycle. In the field of robotics, this design is often referred to as "behavior-based" or "schema-based." The major contribution of this work is merging behavior-based robotics with plan- based human-computer interaction."

We use non-binary coding, elitist strategy, increasing mutation rate, extinction, and immigration strategy to improve the simple genetic algorithms in this study. We expect that the search technique can avoid falling into the local optimum due to the premature convergence, and purse the chance that finding the near-optimal parameters in the larger searching space could be obviously increased. We utilize SIRMs(Single Input Rule Modules) fuzzy controller for the stabilization control of inverted pendulum systems, and the dynamic importance degrees are built such that the angular control of the pendulum takes priority over the position control of the cart. We utilize modified genetic algorithms(MGA) to automatically tuning scaling factors of SIRMs fuzzy controller. From computer simulations, the pendulum control and the cart position control can fastly be stabilized.

Thesis (Ph. D.)--University of Missouri-Columbia, 2003. / Typescript. Vita. Includes bibliographical references (leaves 209-215). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2003. / Typescript. Vita. Includes bibliographical references (leaves 209-215). Also available on the Internet.

Thesis (Ph. D.)--Florida State University, 2003. / Advisor: Ladislav Kohout, Florida State University, College of Arts and Sciences, Dept. of Computer Science. Title and description from dissertation home page (viewed Mar. 9, 2004). Includes bibliographical references.

Thesis (Ph. D.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 379-401).

Thesis (Ph. D.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 354-392).

Thesis (Ph. D.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 196-209).

No description available.