Task level feedback control of a robot based on the integration of real-time recognition and motion planning

摘要

This paper introduces a methodology that will allow robots to execute tasks autonomously and with a high degree of success. Taking as an example the mobility of a robot without collision in a dynamic environment, a task-level feedback controlsystem is proposed. The key idea is to incorporate the real-time recognition and motion planning functions into the task control loop. For real-time recognition of the environment, mark-based vision is proposed to be systematized. In addition, algorithmto do a global motion planning in the environment where movable obstacles exist is proposed to be implemented. By integrating the real-time recognition and motion planning, we succeed in forming a control loop for the task.