In this study, two algorithms for real-time navigation of mobile robots in unknown environments is presented. The first approach integrates a novel learning algorithm derived from Skinner's operant conditioning and a shunting neural dynamics model, producing the capability of path planning in unknown and cluttered environments, after training and assistance with an angular velocity map. Second, a fuzzy logic based bio-inspired system is developed for mobile robot navigation. Based on a modified Braitenberg's automata model, a bio-inspired hybrid fuzzy neural network structure is designed to control the robot, where the neural network weights are obtained from the fuzzy system. The effectiveness of both proposed methods are validated by simulation studies. In comparison to the Chang-Gaudiano algorithm under the same conditions, the proposed bio-inspired algorithm not only allows the robot to navigate efficiently in cluttered environments, but also significantly improves the computational and training time. This bio-inspired algorithm was successfully implemented on a real mobile robot for indoor obstacle avoidance.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:OGU.10214/4008 |
| Date | 14 September 2012 |
| Creators | Wang, Lei |
| Contributors | Simon X., Yang |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Rights | http://creativecommons.org/licenses/by/2.5/ca/ |
Page generated in 0.0144 seconds