A task management design for task-based control architecture for personal robots

摘要

Nowadays, many robots are used in home environments. These are servants for people and personal usage. So, we named these robots personal robot. As the possible applications for personal robots increase and involve more complicated environments and tasks, they become to have very complicated kinematics configurations and need more appropriate control architectures. Previous control architectures have fixed and simple configurations that are optimized for specific applications or with limited flexibility. Consequently, they fail to provide the flexibility necessary for various robot kinematical configurations as well as various tasks. To overcome this problem, we proposed a new personal robot platform and task-based control architecture called "supervised hybrid architecture (SHA)". This platform is composed of reconfigurable modules. SHA is based on supervised organization and distributed arbitration of hybrid controls of reconfigurable deliberative and reactive modules. It is composed of upper level hybrid control for high-level intelligence to interact with human and to plan tasks, as well as lower level hybrid control to allow low-level intelligence for prompt reaction in each robot configuration module. Through these double layers of the hybrid controller, we could easily provide the flexibility needed for so many different kinematical configurations and tasks. In this paper, we will show that how organize this architecture and how operate various tasks in SHA. We will design the task manager for SHA. This manager uses decision tree to make sub tasks and task library to select sequence of the sub tasks. Decision tree checks current status of the robot and decides robot to do. We will show simple example for the proposed architecture are implemented in the platform and tested to show how it works successfully.