碩士 / 國立中興大學 / 電機工程學系所 / 101 / This paper proposes navigation of multiple wheeled mobile robots cooperatively carrying an object in unknown environments. In the navigation process, 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 adaptive fusion of continuous ant colony and particle swarm optimization algorithms (AF-CACPSO) is proposed. All of the free parameters in a fuzzy controller (FC) are learned through the AF-CACPSO, which avoids the time-consuming manual design task. The AF-CACPSO-designed FC is first applied to the control of a single robot for the OBF behavior in a training environment. The learning approach is then applied to address the cooperative OBF problem of two/three cooperative robots, where auxiliary FCs for the other robots are designed using the AF-CACPSO. For the cooperative TS behavior, a rule for coordination of the two/three robots is proposed. In navigation, a cooperative behavior supervisor is proposed to coordinate the learned cooperative OBF behavior and the cooperative TS behavior, where the problem of dead cycles is considered. Performance of the AF-CACPSO is verified through comparisons with various population-based optimization algorithms (POAs) in the cooperative OBF behavior learning problem. Successful navigation of two/three cooperative robots in simulations and experiments verify effectiveness of the proposed evolutionary fuzzy control and navigation approaches.
| Identifer | oai:union.ndltd.org:TW/101NCHU5441037 |
| Date | January 2013 |
| Creators | Ming-Zhi Lai, 賴明志 |
| 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 | 51 |
Page generated in 0.0018 seconds