碩士 / 國立中興大學 / 電機工程學系所 / 105 / This thesis proposes a new method for the navigation of multiple wheeled mobile robots cooperatively carrying an object in unknown environments. In the navigation course, multiple robots cooperatively perform either an obstacle-boundary-following (OBF) or a target seeking (TS) behavior to reach a target. Evolutionary fuzzy control of two/three robots in executing the cooperative OBF behavior through a data-driven advanced multi-objective continuous ant colony optimization (AMO-FCACO) is used. The AMO-FCACO is used to learn all unconstrained parameters in a fuzzy controller (FC), which avoids the time-consuming manual design task. The AMO-FCACO-designed FC is first applied to control a single robot for the OBF behavior in a training environment, where training environment includes both inner and outer corners with right angles. The learning approach is then applied to solve the cooperative OBF problem of two/three cooperative robots, where AMO-FCACO is used to design complementary FCs for the other robots. Performance of the AMO-FCACO is verified through comparisons with various population-based optimization algorithms in the cooperative OBF behavior learning problem. In the three cooperative robots control problem, two online learning approaches using gradient descent and fuzzy Q-learning are proposed to update the parameters of an AMO-FCACO-designed FC for the third robot to track a desired trajectory. For the cooperative TS behavior, this thesis proposes a rule for coordination of the two/three robots. A cooperative behavior supervisor is proposed to coordinate the learned cooperative OBF behavior and the cooperative TS behavior in navigation, where the problem of dead cycles is considered. Successful navigation of two/three cooperative mobile robots carrying an object in several complex environments verifies the evolutionary fuzzy control and navigation methods.
Identifer | oai:union.ndltd.org:TW/105NCHU5441055 |
Date | January 2017 |
Creators | Chen-An Huang, 黃晨安 |
Contributors | 莊家峰 |
Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
Language | en_US |
Detected Language | English |
Type | 學位論文 ; thesis |
Format | 67 |
Page generated in 0.0019 seconds