Publisher's Synopsis
Intelligence takes many forms. This study explores an insight that animals, humans, and autonomous robots can all be analyzed as multi-task autonomous control systems. Biological adaptive systems, the authors argue, can in fact provide a better understanding of intelligence and rationality than that provided by traditional AI.;In this investigation of robot-animal analogies, McFarland and Bosser show that a bee's accuracy in navigating on a cloudy day and a moth's simple but effective hearing mechanisms have as much to teach us about intelligent behaviour as human models. In defining intelligent behaviour, what matters is the behavioural outcome, not the nature of the mechanism by which the outcome is achieved. Similarly, in designing robots capable of intelligent behaviour, what matters is the behavioural outcome.;McFarland and Bosser address the problem of how to assess the consequences of robot behaviour in a way that is meaningful in terms of the robot's intended role, comparing animal and robot in relation to rational behaviour, goal-seeking, task accomplishment, learning, and other important theoretical issues.