Corridor navigation of a mobile robot using a camera and sensors : multi-agent approach
MetadataShow full item record
This thesis addresses two issues in robotic application: an issue concerned with the verification of how well the existing heuristic methods compensate for uncertainty caused by sensing the unstructured environment, and an issue focusing on the design and implementation of a control system that is easily expandable and portable to another robotic platform aiming to future research and application. Using a robot equipped with a minimal set of sensors such as a camera and infrared sensors, our multi-agent based control system is built to tackle various problems encountered during corridor navigation. The control system consists of four agents: an agent responsible for handling sensors, an agent which identifies a corridor using machine vision techniques, an agent which avoids collisions applying fuzzy logic to proximity data, and an agent responsible for locomotion. In the experiments, the robot’s performance demonstrates the feasibility of a multi-agent approach.
Showing items related by title, author, creator and subject.
McClain, Jonathan Thomas (uga, 2004-05)This thesis focuses on the development of a robust architecture for the control of multi-robot teams. In particular, the use of a behavior-based blackboard architecture for multi-robot control is presented, with comparisons ...
Cho, Eunji (uga, 2018-05)This study explores a robotics class of 24 second graders in a Title 1 elementary school located in the southeastern United States. Drawing on Latour’s Actor-Network-Theory and Bakhtin’s notion of hybridity, the findings ...
Barnhard, David Howard (uga, 2005-08)The utilization of multiple robots to map an unknown environment is a challenging problem within Artificial Intelligence. This thesis first presents previous efforts to develop robotic platforms that have demonstrated ...