Steels Luc
Sony Computer Science Laboratory, 6 rue Amyot, 75005 Paris, France.
Philos Trans A Math Phys Eng Sci. 2003 Oct 15;361(1811):2381-95. doi: 10.1098/rsta.2003.1257.
Behaviour-based robotics has always been inspired by earlier cybernetics work such as that of W. Grey Walter. It emphasizes that intelligence can be achieved without the kinds of representations common in symbolic AI systems. The paper argues that such representations might indeed not be needed for many aspects of sensory-motor intelligence but become a crucial issue when bootstrapping to higher levels of cognition. It proposes a scenario in the form of evolutionary language games by which embodied agents develop situated grounded representations adapted to their needs and the conventions emerging in the population.
基于行为的机器人技术一直受到早期控制论研究(如W. 格雷·沃尔特的研究)的启发。它强调,无需符号人工智能系统中常见的那种表征就能实现智能。本文认为,对于感觉运动智能的许多方面而言,这种表征可能确实并非必要,但在向更高层次的认知发展时,却成为一个关键问题。它提出了一种以进化语言游戏形式呈现的设想,通过这种设想,具身智能体能够发展出适应自身需求以及群体中出现的惯例的情境化基础表征。