TY - JOUR AB - Mobile robots with dextrous hands and sophisticated sensory systems will require intelligent, knowledge‐based, expert controllers. A design is developed for a robot controller which can acquire task knowledge as it interacts in the world with its human users. The design is based on four reasonable assumptions which lead to a theoretical framework for robot learning systems. The framework is called a multiple‐context learning system. It is a production system with multiple templates for forming productions as the system interacts with the world. Elaborations of the framework and experimental tests of the system are discussed. VL - 20 IS - 4 SN - 0368-492X DO - 10.1108/eb005892 UR - https://doi.org/10.1108/eb005892 AU - Andreae John H. AU - MacDonald Bruce A. PY - 1991 Y1 - 1991/01/01 TI - Expert Control for a Robot Body T2 - Kybernetes PB - MCB UP Ltd SP - 28 EP - 54 Y2 - 2024/03/29 ER -