Learning for skill refinement

Abstract

It is claimed that 'robotics' is not a test bed for AI but should involve a research frontier relating to the physics underlying human activities such as perception, remembering, planning, practice, and skill. In addition to traditional AI and neural network approaches, other domains that can account for any aspect of human intellectual behavior must be exploited, and tools that actualize real implementation of intelligence in machines need to be devised. A practice-based learning domain for skill refinement and a design tool for a signal-based structured information base for skill acquisition are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>