In good hands: A case for improving robotic dexterity

摘要

Twenty-first-century roboticists envision robots capable of sorting objects and packaging them, of chopping vegetables and folding clothes. But although many today believe that the only factors necessary for robots to achieve dexterous manipulation are data and artificial intelligence (AI), managing all the mundane manipulations that humans perform daily requires constant adaptation to changing conditions. These operations include tasks demanding millisecond-level responses to prevent irreparable damage, such as quickly stabilizing a slipping package or halting a knife just before it cuts into a table. Although recent advances in intelligent robot control have considerably expanded-and will continue to expand-the range and complexity of tasks that robots can perform, AI, data, and control theory alone are not enough. A brain cannot manipulate items effectively without a body-and specifically hands-suited to the task.