John Laird Authors Book on Soar Cognitive Architecture

Professor John E. Laird, the John L. Tishman Professor of Engineering in the EECS Department, has authored a new book entitled "The Soar Cognitive Architecture," which has been published by MIT Press.
John Laird Enlarge
Prof. John Laird

Professor John E. Laird, the John L. Tishman Professor of Engineering in the EECS Department, has authored a new book entitled “The Soar Cognitive Architecture,” which has been published by MIT Press.

The book describes Soar, a general cognitive architecture that integrates knowledge-intensive reasoning, reactive execution, hierarchical reasoning, planning, and learning from experience, with the goal of creating a general computational system that has the same cognitive abilities as humans. In contrast, most AI systems are designed to solve only one type of problem, such as playing chess, searching the Internet, or scheduling aircraft departures. Soar is both a software system for agent development and a theory of what computational structures are necessary to support human-level agents.

The book offers the definitive presentation of Soar from theoretical and practical perspectives, providing comprehensive descriptions of fundamental aspects and new components. The current version of Soar features major extensions, adding reinforcement learning, semantic memory, episodic memory, mental imagery, and an appraisal-based model of emotion. The book describes details of Soar’s component memories and processes and offers demonstrations of individual components, components working in combination, and real-world applications. Beyond these functional considerations, the book also proposes requirements for general cognitive architectures and explicitly evaluates how well Soar meets those requirements.

Prof. Laird’s major research interest is in creating human-level artificial intelligent entities, with an emphasis on the underlying cognitive architecture. Since 1981, his work has centered on the development and use of the Soar cognitive architecture. He is working to extend Soar to include reinforcement learning, episodic memory, semantic memory, clustering, mental imagery, and emotion-inspired processing.

Prof. Laird is a member of the Artificial Intelligence Laboratory in the U-M EECS Department. He holds a B.S. from the University of Michigan and a Ph.D. in Computer Science from Carnegie Mellon University, and joined the Michigan faculty in 1986. He is a founder of Soar Technology, an Ann Arbor company specializing in the creation of autonomous AI entities. He is a Fellow of AAAI, ACM, the Cognitive Science Society, and AAAS.

Artificial Intelligence; Autonomy, AI & Robotics; John Laird; Machine Learning; Research News