Application of Genetic Algorithm Based on Objective Model to Corridor Recognition
-
摘要: 为了保证移动机器人能够沿着走廊自动行走并具有一定的智能水平,工作环境的辨识就显得至关重要.同时考虑到控制的实时性,提出了一种基于目标模型的模型匹配的走廊辨识方法.利用遗传算法对未处理的灰度图像中的走廊影像进行匹配,从而使移动机器人自动地适应复杂环境,实现了模型对灯光条件变化以及包括干扰物等环境噪声的鲁棒性,并经实际走廊图像试验验证了辨识效果.Abstract: It's very important to recognize the working environment for a mobile robot when it travels in the corridor automatically with its possible intelligence.Taking real-time control of mobile robot into consideration,a corridor recognition method with model matching based on objective model is presented.The image of the corridor in unpro-cessed gray image is matched using genetic algorithm by which the mobile robot can automatically adapt to the complex environ-ment and the proposed model with high robustness against noise such as lighting condition variations and obstacles is realized.The recognition effect is verified with real corridor images.
-
Keywords:
- genetic algorithm /
- corridor recognition /
- model matching
-
-
[1] Guo L A,Akazawa H,Izumi M,et al.A method of model-based object recognition[A].Proceedings of the 1996 Japan-USA Symposium on Flexible Automation[C].New York,NJ,USA:ASME,1996.905~912. [2] Nagata T,Zha H B.Recognizing and locating a known object from multiple images[J].IEEE Transactions on Robotics and Automation,1991,7(4):434~447. [3] Talluri R,Aggarwal J K.Mobile robot self-location using modelimage feature correspondence[J].IEEE Transactions on Robotics and Automation,1996,12(1):63~77. [4] 王小平,曹立明.遗传算法--理论、应用与软件实现[M].西安:西安交通大学出版社,2002.
计量
- 文章访问数: 1480
- HTML全文浏览量: 0
- PDF下载量: 176