Human computer interaction based on a multi-agent system
M.C. Thomas, S. Gallesio, Bryce Sanchez, Jean‐Yves Tigli
- 发表年份
- 2002
- 引用次数
- 2
摘要
Our human-computer interaction must be designed to use a multi-agent system. Indeed, this interface is a part of a global system which is a software architecture for robots control. The aim is to ease the designer, the user and the operator task, from mission specification to mission execution. The interaction software assists the human operator. In addition, our methodology is generic and can be more easily applied to any process control and application using a multi-agent system. This involves the design of agent classes with their specialized graphical interfaces; the specification of agents from the easier interface; (a sensor agent cannot be specified in the same way as a strategy agent); and the control of a process, by choosing of the best representation of these agents. Thus our system must not only manage agents, but also builds agents (off and on line). To design agents, we propose a structure for the implementation based on an object-oriented conception; for the same reason, we have chosen the graphical tool Stk. The first experiments use our minirobot Khepera for obstacles avoidance missions.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991