People often use language to guide action in the real world. These actions frequently involve objects in the immediate physical environment, and therefore engage systems responsible for visual perception and complex motor control in addition to language processing. This book explores how spoken language is comprehended and produced when a person is confronted with a visual world and a specific task to perform on it. The chapters, written by major figures in psycholinguistics and visual cognition, cover topics such as scene processing, language comprehension, language production, and the visual-world methodology. The book ties together the evolutionarily significant domains of language, vision, and action, and will be indispensable to scientists working in these areas.