Multiobjective decision making on a mobile robot /
This dissertation discusses the use of fuzzy logic based decision making in autonomous robotics. This technique is shown to be beneficial when using autonomous mobile robots in unstructured environments. In the past researchers have used teleoperated robots when working in environments such as lunar...
| Main Author: | |
|---|---|
| Format: | Thesis Book |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
1999.
|
| Subjects: | |
| Online Access: | http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=731686781&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD |
| Summary: | This dissertation discusses the use of fuzzy logic based decision making in autonomous robotics. This technique is shown to be beneficial when using autonomous mobile robots in unstructured environments. In the past researchers have used teleoperated robots when working in environments such as lunar, hazardous waste, or hostile military zones. Operating these kinds of robots can be fatiguing for humans. As a result, artificial intelligence, neural networks, and fuzzy logic have been suggested as means to increase the autonomy of mobile robots. In particular, fuzzy if-then rules and fuzzy logic control have been used extensively in mobile robotic application where for instance passage through multiple obstacles has been of primary concern. In this work we introduce the notion of fuzzy multiobjective decision making to the problem of navigation of mobile robots in unstructured environments. Multiobjective decision making can be used in various applications including personnel selection, scheduling, construction, finance, and design, and manufacturing. In static situations or applications, persons, more than likely, may set all of the objectives and preferences before starting the decision making process. This research will use multiobjective decision making in a dynamic environment. The mobile robot uses its sensors to detect the obstacles. The objectives and preferences, as much as possible, are calculated based on the location of the obstacles in relation to the mobile robot. This process is comparable to human decision-making where an assessment of the surroundings and one's own capability provides the basis for navigating and moving around in unstructured environments. In particular it is shown that the proposed approach offers a viable alternative to existing approaches to mobile robotics by providing a flexible architecture for addressing the multiplicity of factors that impact motion planning. |
|---|---|
| Item Description: | Vita. "Major Subject: Mechanical Engineering". |
| Physical Description: | xii, 118 leaves : illustrations ; 28 cm. Issued also on microfiche from University Microfilm Inc. |
| Bibliography: | Includes bibliographical references (leaves 83-94). |