Architectures for functional imagination
Architectures for functional imagination
复制标题
DOI：
10.1016/j.neucom.2008.06.016
复制
发表时间：
2009-01-01
期刊：
影响因子：
6
通讯作者：
Holland, Owen
中科院分区：
文献类型：
--
作者：
Marques, Hugo Gravato;Holland, Owen
想象力可以被广义地定义为对智能体的传感器无法直接获得的信息的操纵。然而，想象力的话题提出了代表性的、生理学的和现象学的问题，如果不使用身体作为参考点，这些问题就无法轻易解决。在这个框架内，我们定义功能性想象的机制，允许一个具体的代理模拟自己的行动和他们的感官后果内部，并提取这样做的行为的好处。在本文中，我们提出了五个必要和充分的要求，实现功能性想象力，以及一个最小的架构，满足所有这些标准。我们还提出了一个分类可能的架构，根据其主要属性。最后，我们描述了一些简单的架构设计使用这些原则和模拟和真实的机器人，包括一个非常复杂的拟人的实验。(C)2008 Elsevier B.V.保留所有权利。
Imagination can be defined broadly as the manipulation of information that is not directly available to an agent's sensors. However, the topic of imagination raises representational, physiological, and phenomenological issues that cannot be tackled easily without using the body as a reference point. Within this framework, we define functional imagination as the mechanism that allows an embodied agent to simulate its own actions and their sensory consequences internally, and to extract behavioural benefits from doing so. In this paper, we present five necessary and sufficient requirements for the implementation of functional imagination, as well as a minimal architecture that meets all these criteria. We also present a taxonomy for categorising possible architectures according to their main attributes. Finally, we describe experiments with some simple architectures designed using these principles and implemented on simulated and real robots, including an extremely complex anthropomimetic humanoid. (C) 2008 Elsevier B.V. All rights reserved.