Progressive Goal-directed Reasoning for Real-time Ai Systems

Real-time performance is increasingly attracting the attention of the artiicial intelligence (AI) community. In spite of their success in various applications, classical AI systems are unsatisfactory when applied to real-time applications. In this paper, we point out the problems raised by integration of real-time capabilities into multi-agent architectures. We present rst the main requirements for real-time applications. Then we describe the ability of goal-directed reasoning to address the reactivity and guarantee response time in RT-SOS (Real-Time Society Of Specialists) in which asynchronous acquisition, interruptible reasoning, progressive reasoning and adaptive reasoning contribute to meet the real-time requirements.