Supervised Autonomy: A Framework for Human-Robot Systems Development |
| |
Authors: | Gordon Cheng Alexander Zelinsky |
| |
Affiliation: | (1) Department of Systems Engineering, Research School of Information Sciences and Engineering, The Australian National University, Canberra, ACT 0200, Australia |
| |
Abstract: | In this paper we present a paradigm for robot control, Supervised Autonomy. Supervised Autonomy is a framework, which facilitates the development of human robot systems. The components which this framework embraces has been devised in a human-oriented manner, to augment users in accomplishing their task. The general concept of our paradigm is to incorporate supervisory control with a qualitative approach for the control of robots. Supervisory control does not rely on human users to perform all the basic functions of perception and action in a system. The approach we have taken shifts all basic autonomous functions to the physical robot agent, integrated with a set of qualitative instructions, in combination with a simple graphical user interface, and together with suitable feedback form the complete framework. Experimental results of applying this framework to the use of a mobile robot teleoperation system are presented. The system we have developed make extensive use of behavior-based control technology, embracing a number of real-time visual behaviours, together with a set of intuitive instructions designed for the navigation of a mobile robot. |
| |
Keywords: | supervised autonomy mobile robot navigation teleoperation human robot interface visual navigation behavior-based control visual behaviors supervisory control |
本文献已被 SpringerLink 等数据库收录! |
|