A Robot Planning Structure Using Production Rules

Robot plan generation is a f ie ld which engendered the development of AI languages and r u l e based expert systems. Ut i l izat ion of these lat ter concepts permits a f l e x i b l e formalism for robot planning research. We present a robot plan-generation arch i tecture and i t s appl icat ion to a r e a l world mobile robot system. The system undergoes tests through i t s u t i l i z a t i o n in the IIILARE robot project (Ci ral t, e_t jal_, 1984). Though the a r t i c l e concentrates on planning, execution monitoring and error recovery are discussed. The system includes models of i ts synergistic environment as well SR of i ts sensors and ef fectors ( i .e . operators). I t s rules embody both planning spec i f ic and domair specific knowledge. The system gains general i ty and adaptiveness through the use of planning va r i ables which provide constraints to the plan generation system. It is implemented in an e f f i c i e n t compiled Production System language (PS1).