A task-based and resource-aware software-architecture generation method for intelligent service robots

Abstract

Intelligent service robots provide various services to user. In order to provide services more reliably, intelligent service robots need to consider various factors, such as their surrounding environments, user’s changing requirements, and constrained resources. To realize this, most of the intelligent service robots are controlled based on a task-based control system, which generates a task plan that consists of a sequence of actions, and executes the actions by invoking the corresponding functions. However, this task-based control system that usually consists of three layer did not seriously consider resource factors even though intelligent service robots have limited resources (limited computational power, memory space, and network bandwidth). Also, system specific information did not consider during task generation. Therefore, in this thesis, we propose a mechanism for intelligent service robots to efficiently use their resources on-demand by separating system specific information from task generation. We define reusable software-architectures corresponding to each action of a task plan, and provide a way of using the limited resources by minimizing redundant software components and only maintaining components for current action. We conducted an experiment of this mechanism for an infotainment robot. The experiment shows the effectiveness of our mechanism.