Most current work in robotics emphasizes basic-level tasks like sensory processing, path planning, manipulator design and control, reactive agents, artificial insects, etc. In contrast, research in cognitive robotics is concerned with the theory and the implementation of robots that reason, act and perceive in changing, incompletely known, unpredictable environments. Such robots must have higher level cognitive functions that involve reasoning, for example, about goals, actions, when to perceive and what to look for, the cognitive states of other agents, time, collaborative task execution, etc. In short, cognitive robotics is concerned with integrating reasoning, perception and action within a uniform theoretical and implementation framework.

Recently, cognitive robotics has attracted the interest of several research groups, and the last few years has witnessed a good deal of work on knowledge representation and especially on reasoning about actions related to actual robots. Cognitive robotics offers a fruitful approach to the design and implementation of autonomous agents of the future.