The cooperation of heterogeneous mobile robot configurations in advanced manufacturing environments.

Abstract

Cooperation of Multiple Mobile Robot Systems (MMRS) have drawn increasing attention in recent years since these systems have the ability to perform complex tasks more efficiently compared to Single Mobile Robot Systems (SMRS). An implementation of a cooperative MMRS in a manufacturing environment can, for example, solve the issue of bottlenecks in a production line, whereas the limitations of a SMRS can lead to a lot of problems in terms of time wastage, loss of revenue, poor quality products and dissatisfied customers. The study of cooperation in heterogeneous robot teams has evolved due to the engineering and economic benefits attribute as well as the existence of diversities in homogeneous robot teams. The challenge of cooperation in these systems is a result of the task taxonomies and fundamental abilities of each robot in the team; there is therefore a need for an Artificial Intelligence (AI) system that processes these heterogeneities to facilitate robot cooperation. This dissertation focuses on the research, design and development of an artificial intelligence for a team of heterogeneous mobile robots. The application of the system was directed towards advanced manufacturing systems, however, it can be adapted to search and rescue tasks. An essential component of the AI design is the machine learning algorithm which was used to predict suitable goal destinations for each mobile robot, given a set of input parameters. Mobile robot autonomy was achieved through the development of an obstacle avoidance and navigation system. The AI was also interfaced to a Supervisory Control and Data Acquisition System (SCADA) which facilitates end-user interaction - a vital ingredient to manufacturing automation systems.