The design of a framework to control multiple semi-autonomous mobile robots is presented. The goals are to create a flexible framework that allows easy task reconfiguration for a fleet of mobile robots, and to provide a means of off-loading computationally intensive tasks to a central server. Four major components are specified: controllable devices, application servers, an application directory, and a mobile management system. Remote firmware upgrades via the mobile management system are achieved with the remotely managed operating system framework or RMOS. A prototype was created using field programmable gate arrays and system on a programmable chip technology from Altera. It was built with the application of selective herbicide spraying in mind. Although the prototype was a successful implementation of the designed framework, selective herbicide application was not implemented. A broad-leaf weed detection algorithm using Boltzmann machines was investigated. Its performance was good, but similar to that obtained by a statistical analysis of the input images of a lawn.
| Identifer | oai:union.ndltd.org:MANITOBA/oai:mspace.lib.umanitoba.ca:1993/4396 |
| Date | 21 January 2011 |
| Creators | Sanders, David Marc |
| Contributors | McLeod, Robert (Electrical and Computer Engineering), Ferens, Ken (Electrical and Computer Engineering) Anderson, John (Computer Science) |
| Source Sets | University of Manitoba Canada |
| Language | en_US |
| Detected Language | English |
Page generated in 0.002 seconds