摘要
感知与交互既是智能机器重要且基本的能力和组成部分,也是智能机器从现实中学习和获得知识的重要甚至唯一手段.过去20年中感知与交互系统的研究往往是面向限定域的,并且在若干领域取得了显著的进步.随着服务机器人、无人驾驶车等的发展,感知与交互系统将不可避免地需要面对真实世界的挑战.本文简要地回顾了感知与交互领域的发展历程,提出了8个面向真实世界感知与交互的挑战.解决这些问题,有助于将现有智能机器应对外界的能力从特定领域的"专家"提升到在一般意义上"常人"级水平的感知与交互.
Perception and interaction are the most important and essential parts of an intelligent machine. They are crucial and even unique channels by which to learn from the real world. In the past two decades, there has been significant progress in closed world research on perception and/or interaction. With the current rapid developments in the areas of service robots and unmanned vehicles, perception and interaction are confronted with challenges from the real world. This paper briefly reviews the history of computer perception and interaction,and lists eight problems in real world perception and interaction that, if solved, will elevate the perception and interaction capabilities of intelligent machines from a specialist- to human-level in the real world.
出处
《中国科学：信息科学》
CSCD
北大核心
2016年第8期969-981,共13页
Scientia Sinica(Informationis)
基金
国家自然科学基金(批准号:61390510)资助项目
关键词
感知
交互
计算机视觉
机器人
perception
interaction
computer vision
robot
