摘要
移动机器人在不确定环境中的目标识别技术是自主导航及复杂任务分解的一项关键技术。本文利用自行设计的多超声波传感器探测系统感知外界环境,提出了基于目标原型的目标识别和对感兴趣目标的主动探测方法。根据多超声波传感器的TOF(Time-of-Flight)信息,利用Dempster-Shafer证据理论,实现了移动机器人对室内特征环境的准确识别。测试结果及分析验证了该方法的可行性和识别准确性,并且该方法适用于室内机器人运动中的实时探测。
Target identification for mobile robots in uncertain environments is one of the key techniques of autonomous navigation and task decomposition. With sensing the environments by multi-ultrasonic sensor detecting system, the method of target identification and further active detecting for interesting target is proposed, which achieves exact identification of the indoor environments with special features for mobile robot. In this paper, different environment features are classified and a multi-ultrasonic sensor system is used to provide relative TOF (Time-of-Flight) information. According to the TOF information, different decisions are made through Dempster-Shafer evidential reasoning and further active detecting. The experimental results and analysis show its feasibility and high veracity, which is applicable for indoor robot real-time detecting.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2005年第5期602-607,共6页
Pattern Recognition and Artificial Intelligence
关键词
目标识别
主动探测
多超声波传感器系统
自主式移动机器人
Target Identification, Active Detecting, Multi- Ultrasonic Sensor System, Autonomous Mobile Robot