AbstractThis thesis documents the research that has led to the development, in prototype form, of a modular sensing system for use in a robot's work cell. The system implemented overcomes one of the major limitations of existing sensing systems, that is the difficulty of altering their sensing characteristics. The majority of sensing systems that are currently available are inflexible in that the addition of extra sensors requires, at the very least, substantial changes to both hardware and software. What these systems require is a facility through which users can easily, and readily, make changes to the configuration of the sensors they employ.
In the modular system described, the sensors that provide the information about the robot's work cell are independent of the algorithms that make use of the information. That is, the sensors do not need any knowledge as to when or how the information they provide will be used. Similarly, the algorithms that make use of the data do not need any knowledge as to the provider of the data. This separation of data provider from data user enables the software that controls the sensors (and even the sensors themselves) to be upgraded without corresponding changes to the data user software. Additional sensors can easily be added to the system while redundant sensors can simply be removed.
The location of objects within the robot's workspace is achieved by building a model of the workspace using the information provided by a number of sensors.
As a prerequisite to model construction three problems had to be addressed. Firstly, the information extracted from different sensors is generally at different resolutions. Secondly, the representation of 3-D space requires large amounts of computer memory. Thirdly, the production of the 3-D model, particularly when a large number of sensors are involved requires a substantial amount of processor time. The first two problems were addressed using a data structure that allowed compact data storage, while the final problem was reduced by identifying parallel aspects of the processing and implementing them on a network of transputers.
After the objects within the robot's workspace have been located, the next stage is to identify them. The identification is achieved by calculating the degree of match between measurable characteristics of the object to be identified and the same measurable characteristics of known objects. The degree of match, which is similar but not identical to the correlation function, between the object to be identified and each known object is then used to determine, if possible, the required identity of the object.
The work contained within the thesis not only demonstrates the feasibility and benefits of a modular sensing system, over traditional sensing system, but has brought to light some points that will need further thought before a fully functional system is produced. The last chapter contains, in addition to a full and detailed list of conclusions made during the research, a summary of some of these areas that still require further work.
|Date of Award||Sep 1992|
|Supervisor||Glyn Roberts (Supervisor) & R. A. Davies (Supervisor)|