服务机器人是我国急需发展的产业。其相关技术在近年来取得较大进步，但总体来看智能水平偏低，特别是对环境的认知和目标的识别能力和效率方面存在较大不足。研究自然环境下面向服务机器人的环境认知和目标行为识别，对于提升服务机器人的智能水平、促进服务机器人产业的发展极为重要。本项目将从图像特征的高效表示、多传感器数据的配准融合两个关键问题入手，着力提高在复杂环境下服务机器人环境认知和目标行为识别的能力和效率，并在服务机器人实际系统上进行验证和完善。本项目将形成自成体系的自主创新成果，在国际上形成一定学术影响，为机器人的环境认知、目标行为识别等应用提供理论和方法的支持。

Service robot industry is urgent to be developed in China. While great progress has been made for the related technologies, the overall intelligence is still at a low level, especially the large deficiency in the ability and efficiency of environment perception and object recognition. The study on the environment perception and object recognition for service robots in natural environment is vital to improving the intelligence of service robots and promoting the development of service robot industry. This project aims at improving the ability and efficiency of environment perception and object behavior recognition for service robots in complex environment, focuses on the two key issues of the efficient representation of image feature and the registration and fusion of multi-sensor data. On the basis of the above works, the problems of environment perception and object behavior recognition for service robots will be studied. This project will result in self-contained independent innovation achievements, make academic impacts in the international community and provide the theoretical and methodological support for the environment perception and object recognition of robots.