This book uses an intelligent agent as the unifying theme throughout — i.e., the problem of AI is to describe and build agents that receive percepts from the environment and perform actions, and each such agent is implemented by a function that maps percepts to actions. covers different ways to represent these functions, such as production systems, reactive agents, logical planners and decision- theoretic systems explains the role of learning as extending the reach of the designer into unknown environments, and shows how it constrains agent design, favoring explicit knowledge representation and reasoning includes a thorough, up-to-date and integrated treatment of robotics and vision, written by John Canny and Jitendra Malik, two of the leading exponents in their respective fields analyzes basic techniques for addressing complexity (use of approximation, compilation, anytime algorithms, hierarchical abstraction) as general sources of power Covers areas that are sometimes under-emphasized— reasoning under uncertainty, learning, natural language, vision and robotics —and explains in detail some of the more recent ideas in the field —e.g., simulated annealing, memory-bounded search, global ontologies, dynamic belief networks, neural nets, inductive logic programming, computational learning theory, and reinforcement learning. Tackles AI's philosophical critics head-on. Gives equal emphasis to theory and practice—considers the basic concepts and mathematical methods of AI, what can and cannot be done with today's technology, at what cost, and using what techniques. Integrates state-of-the art AI techniques intointelligent agent designs, using examples and exercises to lead the student from simple, reactive agents to full knowledge-based agents with natural language capabilities. Includes over 75 algorithms, and a variety of simulated environments for testing agent designs. presents