Performing complex assembly tasks requires decisional capabilities available on-line, in order to handle various events (sensor conditions, part arrivals, failure detection...), that occur during execution. In this paper, we describe NNS, a complete on-line system for multi-robot assembly workcells, that deals with problems of execution monitoring, action scheduling, and failure diagnosis and recovery. NNS is distributed in different decisional layers with their own reasoning methods and state representation; it uses an "execution model" that embeds various knowledge bases built off-line. This approach fits well with requirements of flexibility and efficiency.

This paper is divided into four sections. The first section discusses Flexible Assembly Cell (FAC) programming requirements. Sections 2 and 3 present an approach to FAC modelling and programming. The intended objective is to build a programming and decisional environment which allows construction of assembly applications, and to endow the on-line system with decision-making capabilities. The last section describes the current state of an actual system which is a first approach to meeting the discussed requirements.