How the SP Theory of Intelligence may help in the advancement of knowledge in self-sufficient robots

The SP System, meaning the SP Theory of Intelligence and its realisation in the SP Computer Model, is the product of a lengthy programme of research, which now provides solutions or potential solutions to several problems in AI research [1]. There is an extended overview of the SP System in [2], and there is a much more comprehensive description in [3]. Details of related publications, with download links, are on www.cognitionresearch.org/sp.htm. This presentation focusses on autonomous robots and how the SP System may prove useful in the development of intelligence in such robots. A peer-reviewed, published, paper about this is in [4]. The main parts of this presentation are described in the following three sections. Problems in the development of intelligence in autonomous robots The main problems in the development of intelligence in autonomous robots are these: • How to increase the computational efficiency in robots, with reductions in energy consumption, and in the size and weight of computers. • How to achieve human-like versatility in intelligence. • How to achieve human-like adaptability in intelligence. Outline of the SP theory and the SP Computer Model The overarching goal in the development of the SP System has been to search for a framework that would simplify and integrate observations and concepts across artificial intelligence, mainstream computing, mathematics, and human learning, perception, and cognition. Despite the ambition of this goal, it seems that promising solutions have been found.

Author(s): J Gerard Wolff

Abstract | PDF

Share This Article